Maintained by Difan Deng and Marius Lindauer.
The following list considers papers related to neural architecture search. It is by no means complete. If you miss a paper on the list, please let us know.
Please note that although NAS methods steadily improve, the quality of empirical evaluations in this field are still lagging behind compared to other areas in machine learning, AI and optimization. We would therefore like to share some best practices for empirical evaluations of NAS methods, which we believe will facilitate sustained and measurable progress in the field. If you are interested in a teaser, please read our blog post or directly jump to our checklist.
Transformers have gained increasing popularity in different domains. For a comprehensive list of papers focusing on Neural Architecture Search for Transformer-Based spaces, the awesome-transformer-search repo is all you need.
2021
1425.
Clemens, John
MLDS: A Dataset for Weight-Space Analysis of Neural Networks Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2104-10555,
title = {MLDS: A Dataset for Weight-Space Analysis of Neural Networks},
author = {John Clemens},
url = {https://arxiv.org/abs/2104.10555},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.10555},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1424.
Pasini, Massimiliano Lupo; Yin, Junqi; Li, Ying Wai; Eisenbach, Markus
A scalable algorithm for the optimization of neural network architectures Journal Article
In: Parallel Computing, vol. 104-105, pp. 102788, 2021, ISSN: 0167-8191.
@article{LUPOPASINI2021102788,
title = {A scalable algorithm for the optimization of neural network architectures},
author = {Massimiliano Lupo Pasini and Junqi Yin and Ying Wai Li and Markus Eisenbach},
url = {https://www.sciencedirect.com/science/article/pii/S0167819121000430},
doi = {https://doi.org/10.1016/j.parco.2021.102788},
issn = {0167-8191},
year = {2021},
date = {2021-01-01},
journal = {Parallel Computing},
volume = {104-105},
pages = {102788},
abstract = {We propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified by other hyperparameter search algorithms in terms of accuracy and computational cost. Numerical results performed on benchmark datasets show that, for these datasets, our method outperforms state-of-the-art hyperparameter optimization algorithms in terms of attainable predictive performance by the selected neural network architecture, and time-to-solution for the hyperparameter optimization to complete.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
We propose a new scalable method to optimize the architecture of an artificial neural network. The proposed algorithm, called Greedy Search for Neural Network Architecture, aims to determine a neural network with minimal number of layers that is at least as performant as neural networks of the same structure identified by other hyperparameter search algorithms in terms of accuracy and computational cost. Numerical results performed on benchmark datasets show that, for these datasets, our method outperforms state-of-the-art hyperparameter optimization algorithms in terms of attainable predictive performance by the selected neural network architecture, and time-to-solution for the hyperparameter optimization to complete.
1423.
Yang, Zhao; Sun, Qingshuang
Efficient Resource-aware Neural Architecture Search with Dynamic Adaptive Network Sampling Proceedings Article
In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2021.
@inproceedings{9401187,
title = {Efficient Resource-aware Neural Architecture Search with Dynamic Adaptive Network Sampling},
author = {Zhao Yang and Qingshuang Sun},
url = {https://ieeexplore.ieee.org/abstract/document/9401187},
doi = {10.1109/ISCAS51556.2021.9401187},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Symposium on Circuits and Systems (ISCAS)},
pages = {1-5},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1422.
Amer, Mohammed; á, Tom; Liao, Iman Yi
Balancing Accuracy and Latency in Multipath Neural Networks Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2104-12040,
title = {Balancing Accuracy and Latency in Multipath Neural Networks},
author = {Mohammed Amer and Tom á and Iman Yi Liao},
url = {https://arxiv.org/abs/2104.12040},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.12040},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1421.
Lei, Zhou; Yang, Kangkang; Jiang, Kai; Chen, Shengbo
KDAS-ReID: Architecture Search for Person Re-Identification via Distilled Knowledge with Dynamic Temperature Journal Article
In: Algorithms, vol. 14, no. 5, 2021, ISSN: 1999-4893.
@article{a14050137,
title = {KDAS-ReID: Architecture Search for Person Re-Identification via Distilled Knowledge with Dynamic Temperature},
author = {Zhou Lei and Kangkang Yang and Kai Jiang and Shengbo Chen},
url = {https://www.mdpi.com/1999-4893/14/5/137},
doi = {10.3390/a14050137},
issn = {1999-4893},
year = {2021},
date = {2021-01-01},
journal = {Algorithms},
volume = {14},
number = {5},
abstract = {Person re-Identification(Re-ID) based on deep convolutional neural networks (CNNs) achieves remarkable success with its fast speed. However, prevailing Re-ID models are usually built upon backbones that manually design for classification. In order to automatically design an effective Re-ID architecture, we propose a pedestrian re-identification algorithm based on knowledge distillation, called KDAS-ReID. When the knowledge of the teacher model is transferred to the student model, the importance of knowledge in the teacher model will gradually decrease with the improvement of the performance of the student model. Therefore, instead of applying the distillation loss function directly, we consider using dynamic temperatures during the search stage and training stage. Specifically, we start searching and training at a high temperature and gradually reduce the temperature to 1 so that the student model can better learn from the teacher model through soft targets. Extensive experiments demonstrate that KDAS-ReID performs not only better than other state-of-the-art Re-ID models on three benchmarks, but also better than the teacher model based on the ResNet-50 backbone.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Person re-Identification(Re-ID) based on deep convolutional neural networks (CNNs) achieves remarkable success with its fast speed. However, prevailing Re-ID models are usually built upon backbones that manually design for classification. In order to automatically design an effective Re-ID architecture, we propose a pedestrian re-identification algorithm based on knowledge distillation, called KDAS-ReID. When the knowledge of the teacher model is transferred to the student model, the importance of knowledge in the teacher model will gradually decrease with the improvement of the performance of the student model. Therefore, instead of applying the distillation loss function directly, we consider using dynamic temperatures during the search stage and training stage. Specifically, we start searching and training at a high temperature and gradually reduce the temperature to 1 so that the student model can better learn from the teacher model through soft targets. Extensive experiments demonstrate that KDAS-ReID performs not only better than other state-of-the-art Re-ID models on three benchmarks, but also better than the teacher model based on the ResNet-50 backbone.
1420.
Laube, Kevin Alexander; Zell, Andreas
Inter-choice dependent super-network weights Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2104-11522,
title = {Inter-choice dependent super-network weights},
author = {Kevin Alexander Laube and Andreas Zell},
url = {https://arxiv.org/abs/2104.11522},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.11522},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1419.
Chen, Oscal Tzyh-Chiang; Zhang, Yu Cheng; Chang, Yu-Xuan; Chang, Yu-Lung
Iterative Multiple-Path One-Shot NAS for the Optimized Performance Proceedings Article
In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2021.
@inproceedings{9401130,
title = {Iterative Multiple-Path One-Shot NAS for the Optimized Performance},
author = {Oscal Tzyh-Chiang Chen and Yu Cheng Zhang and Yu-Xuan Chang and Yu-Lung Chang},
url = {https://ieeexplore.ieee.org/abstract/document/9401130},
doi = {10.1109/ISCAS51556.2021.9401130},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Symposium on Circuits and Systems (ISCAS)},
pages = {1-5},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1418.
Risso, Matteo; Burrello, Alessio; Pagliari, Daniele Jahier; Benatti, Simone; Macii, Enrico; Benini, Luca; Poncino, Massimo
Robust and Energy-efficient PPG-based Heart-Rate Monitoring Proceedings Article
In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2021.
@inproceedings{9401282,
title = {Robust and Energy-efficient PPG-based Heart-Rate Monitoring},
author = {Matteo Risso and Alessio Burrello and Daniele Jahier Pagliari and Simone Benatti and Enrico Macii and Luca Benini and Massimo Poncino},
url = {https://ieeexplore.ieee.org/abstract/document/9401282},
doi = {10.1109/ISCAS51556.2021.9401282},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Symposium on Circuits and Systems (ISCAS)},
pages = {1-5},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1417.
Byun, Younghoon; Lee, Youngjoo
Rapid Design Space Exploration of Near-Optimal Memory-Reduced DCNN Architecture using Multiple Model Compression Techniques Proceedings Article
In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1-5, 2021.
@inproceedings{9401489,
title = {Rapid Design Space Exploration of Near-Optimal Memory-Reduced DCNN Architecture using Multiple Model Compression Techniques},
author = {Younghoon Byun and Youngjoo Lee},
url = {https://ieeexplore.ieee.org/abstract/document/9401489},
doi = {10.1109/ISCAS51556.2021.9401489},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE International Symposium on Circuits and Systems (ISCAS)},
pages = {1-5},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1416.
Oymak, Samet; Li, Mingchen; Soltanolkotabi, Mahdi
Generalization Guarantees for Neural Architecture Search with Train-Validation Split Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2104-14132,
title = {Generalization Guarantees for Neural Architecture Search with Train-Validation Split},
author = {Samet Oymak and Mingchen Li and Mahdi Soltanolkotabi},
url = {https://arxiv.org/abs/2104.14132},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.14132},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1415.
Yan, Bin; Peng, Houwen; Wu, Kan; Wang, Dong; Fu, Jianlong; Lu, Huchuan
LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2104-14545b,
title = {LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search},
author = {Bin Yan and Houwen Peng and Kan Wu and Dong Wang and Jianlong Fu and Huchuan Lu},
url = {https://arxiv.org/abs/2104.14545},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.14545},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1414.
Yang, Hong; Zhang, Ya-sheng; Yin, Can-bin; Ding, Wen-zhe
In: Defence Technology, 2021, ISSN: 2214-9147.
@article{YANG2021,
title = {Ultra-lightweight CNN design based on neural architecture search and knowledge distillation: A novel method to build the automatic recognition model of space target ISAR images},
author = {Hong Yang and Ya-sheng Zhang and Can-bin Yin and Wen-zhe Ding},
url = {https://www.sciencedirect.com/science/article/pii/S2214914721000763},
doi = {https://doi.org/10.1016/j.dt.2021.04.014},
issn = {2214-9147},
year = {2021},
date = {2021-01-01},
journal = {Defence Technology},
abstract = {In this paper, a novel method of ultra-lightweight convolution neural network (CNN) design based on neural architecture search (NAS) and knowledge distillation (KD) is proposed. It can realize the automatic construction of the space target inverse synthetic aperture radar (ISAR) image recognition model with ultra-lightweight and high accuracy. This method introduces the NAS method into the radar image recognition for the first time, which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model (STIIARM). On this basis, the NAS model's knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure (FSP) distillation method. Thus, the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided, and the ultra-lightweight STIIARM can be obtained. In the method, the Inverted Linear Bottleneck (ILB) and Inverted Residual Block (IRB) are firstly taken as each block's basic structure in CNN. And the expansion ratio, output filter size, number of IRBs, and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space. Then, the recognition accuracy and computational complexity are taken as the objective function and constraint conditions, respectively, and the global optimization model of the CNN architecture search is established. Next, the simulated annealing (SA) algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM directly. After that, based on the three principles of similar block structure, the same corresponding channel number, and the minimum computational complexity, the more lightweight student model is designed, and the FSP matrix pairing between the NAS model and student model is completed. Finally, by minimizing the loss between the FSP matrix pairs of the NAS model and student model, the student model's weight adjustment is completed. Thus the ultra-lightweight and high accuracy STIIARM is obtained. The proposed method's effectiveness is verified by the simulation experiments on the ISAR image dataset of five types of space targets.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
In this paper, a novel method of ultra-lightweight convolution neural network (CNN) design based on neural architecture search (NAS) and knowledge distillation (KD) is proposed. It can realize the automatic construction of the space target inverse synthetic aperture radar (ISAR) image recognition model with ultra-lightweight and high accuracy. This method introduces the NAS method into the radar image recognition for the first time, which solves the time-consuming and labor-consuming problems in the artificial design of the space target ISAR image automatic recognition model (STIIARM). On this basis, the NAS model's knowledge is transferred to the student model with lower computational complexity by the flow of the solution procedure (FSP) distillation method. Thus, the decline of recognition accuracy caused by the direct compression of model structural parameters can be effectively avoided, and the ultra-lightweight STIIARM can be obtained. In the method, the Inverted Linear Bottleneck (ILB) and Inverted Residual Block (IRB) are firstly taken as each block's basic structure in CNN. And the expansion ratio, output filter size, number of IRBs, and convolution kernel size are set as the search parameters to construct a hierarchical decomposition search space. Then, the recognition accuracy and computational complexity are taken as the objective function and constraint conditions, respectively, and the global optimization model of the CNN architecture search is established. Next, the simulated annealing (SA) algorithm is used as the search strategy to search out the lightweight and high accuracy STIIARM directly. After that, based on the three principles of similar block structure, the same corresponding channel number, and the minimum computational complexity, the more lightweight student model is designed, and the FSP matrix pairing between the NAS model and student model is completed. Finally, by minimizing the loss between the FSP matrix pairs of the NAS model and student model, the student model's weight adjustment is completed. Thus the ultra-lightweight and high accuracy STIIARM is obtained. The proposed method's effectiveness is verified by the simulation experiments on the ISAR image dataset of five types of space targets.
1413.
Zhou, Zheng; Li, Tianfu; Zhang, Zilong; Zhao, Zhibin; Sun, Chuang; Yan, Ruqiang; Chen, Xuefeng
Bayesian Differentiable Architecture Search for Efficient Domain Matching Fault Diagnosis Journal Article
In: IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-11, 2021.
@article{9419078,
title = {Bayesian Differentiable Architecture Search for Efficient Domain Matching Fault Diagnosis},
author = {Zheng Zhou and Tianfu Li and Zilong Zhang and Zhibin Zhao and Chuang Sun and Ruqiang Yan and Xuefeng Chen},
url = {https://ieeexplore.ieee.org/abstract/document/9419078},
doi = {10.1109/TIM.2021.3076575},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Instrumentation and Measurement},
volume = {70},
pages = {1-11},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1412.
Zhang, Lingling; Wang, Shaowei; Chang, Xiaojun; Liu, Jun; Ge, Zongyuan; Zheng, Qinghua
Auto-FSL: Searching the Attribute Consistent Network for Few-Shot Learning Journal Article
In: IEEE Transactions on Circuits and Systems for Video Technology, pp. 1-1, 2021.
@article{9419063,
title = {Auto-FSL: Searching the Attribute Consistent Network for Few-Shot Learning},
author = {Lingling Zhang and Shaowei Wang and Xiaojun Chang and Jun Liu and Zongyuan Ge and Qinghua Zheng},
url = {https://ieeexplore.ieee.org/abstract/document/9419063},
doi = {10.1109/TCSVT.2021.3076523},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1411.
Bruggemann, David; Kanakis, Menelaos; Obukhov, Anton; Georgoulis, Stamatios; Gool, Luc Van
Exploring Relational Context for Multi-Task Dense Prediction Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2104-13874,
title = {Exploring Relational Context for Multi-Task Dense Prediction},
author = {David Bruggemann and Menelaos Kanakis and Anton Obukhov and Stamatios Georgoulis and Luc Van Gool},
url = {https://arxiv.org/abs/2104.13874},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2104.13874},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1410.
Valsesia, Diego; Fracastoro, Giulia; Magli, Enrico
Don’t Stack Layers In Graph Neural Networks, Wire Them Randomly Proceedings Article
In: ICLR 2021 Workshop on Geometrical and Topological Representation Learning, 2021.
@inproceedings{Valsesia2021,
title = {Don’t Stack Layers In Graph Neural Networks, Wire Them Randomly},
author = {Valsesia, Diego and Fracastoro, Giulia and Magli, Enrico},
url = {https://openreview.net/pdf/224ad9f05a62ed1b5c7a1a23386bdcd29f717b8a.pdf},
year = {2021},
date = {2021-01-01},
booktitle = {ICLR 2021 Workshop on Geometrical and Topological Representation Learning},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1409.
-, Julia Guerrero; Hauns, Sven; Izquierdo, Sergio; Miotto, Guilherme; Schrodi, Simon; Biedenkapp, Andre; Elsken, Thomas; Deng, Difan; Lindauer, Marius; Hutter, Frank
Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization Proceedings Article
In: 8th ICML Workshop on Automated Machine Learning, 2021.
@inproceedings{DBLP:journals/corr/abs-2105-01015,
title = {Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization},
author = {Julia Guerrero - and Sven Hauns and Sergio Izquierdo and Guilherme Miotto and Simon Schrodi and Andre Biedenkapp and Thomas Elsken and Difan Deng and Marius Lindauer and Frank Hutter},
url = {https://arxiv.org/abs/2105.01015},
year = {2021},
date = {2021-01-01},
booktitle = {8th ICML Workshop on Automated Machine Learning},
journal = {CoRR},
volume = {abs/2105.01015},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1408.
Lv, Jindi; Ye, Qing; Sun, Yanan; Zhao, Juan; Lv, Jiancheng
Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-00693,
title = {Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search},
author = {Jindi Lv and Qing Ye and Yanan Sun and Juan Zhao and Jiancheng Lv},
url = {https://arxiv.org/abs/2105.00693},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.00693},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1407.
Mo, Hyunho; Custode, Leonardo Lucio; Iacca, Giovanni
Evolutionary neural architecture search for remaining useful life prediction Journal Article
In: Applied Soft Computing, vol. 108, pp. 107474, 2021, ISSN: 1568-4946.
@article{MO2021107474,
title = {Evolutionary neural architecture search for remaining useful life prediction},
author = {Hyunho Mo and Leonardo Lucio Custode and Giovanni Iacca},
url = {https://www.sciencedirect.com/science/article/pii/S1568494621003975},
doi = {https://doi.org/10.1016/j.asoc.2021.107474},
issn = {1568-4946},
year = {2021},
date = {2021-01-01},
journal = {Applied Soft Computing},
volume = {108},
pages = {107474},
abstract = {With the advent of Industry 4.0, making accurate predictions of the remaining useful life (RUL) of industrial components has become a crucial aspect in predictive maintenance (PdM). To this aim, various Deep Neural Network (DNN) models have been proposed in the recent literature. However, while the architectures of these models have a large impact on their performance, they are usually determined empirically. To exclude the time-consuming process and the unnecessary computational cost of manually engineering these models, we present a Neural Architecture Search (NAS) technique based on an Evolutionary Algorithm (EA) applied to optimize the architecture of a DNN used to predict the RUL. The EA explores the combinatorial parameter space of a multi-head Convolutional Neural Network with Long Short Term Memory (CNN-LSTM) to search for the best architecture. In particular, our method requires minimum computational resources by making use of an early stopping policy and a history of the evaluated architectures. We dub the proposed method ENAS-PdM. To our knowledge, this is the first work where an EA-based NAS is used to optimize a CNN-LSTM architecture in the field of PdM. In our experiments, we use the well-established Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset from NASA. Compared to the current state-of-the-art, our method obtains better results in terms of two different metrics, RMSE and Score, when aggregating across all the C-MAPSS sub-datasets. Without aggregation, we achieve lower RMSE in 3 out of 4 sub-datasets. Our experimental results verify that the proposed method is a reliable tool for obtaining state-of-the-art RUL predictions and as such it can have a strong impact in several industrial applications, especially those with limited available computing power.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
With the advent of Industry 4.0, making accurate predictions of the remaining useful life (RUL) of industrial components has become a crucial aspect in predictive maintenance (PdM). To this aim, various Deep Neural Network (DNN) models have been proposed in the recent literature. However, while the architectures of these models have a large impact on their performance, they are usually determined empirically. To exclude the time-consuming process and the unnecessary computational cost of manually engineering these models, we present a Neural Architecture Search (NAS) technique based on an Evolutionary Algorithm (EA) applied to optimize the architecture of a DNN used to predict the RUL. The EA explores the combinatorial parameter space of a multi-head Convolutional Neural Network with Long Short Term Memory (CNN-LSTM) to search for the best architecture. In particular, our method requires minimum computational resources by making use of an early stopping policy and a history of the evaluated architectures. We dub the proposed method ENAS-PdM. To our knowledge, this is the first work where an EA-based NAS is used to optimize a CNN-LSTM architecture in the field of PdM. In our experiments, we use the well-established Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset from NASA. Compared to the current state-of-the-art, our method obtains better results in terms of two different metrics, RMSE and Score, when aggregating across all the C-MAPSS sub-datasets. Without aggregation, we achieve lower RMSE in 3 out of 4 sub-datasets. Our experimental results verify that the proposed method is a reliable tool for obtaining state-of-the-art RUL predictions and as such it can have a strong impact in several industrial applications, especially those with limited available computing power.
1406.
Chen, Haoze; Zhang, Zhijie; Zhao, Chenyang; Liu, Jiaqi; Yin, Wuliang; Li, Yanfeng; Wang, Fengxiang; Li, Chao; Lin, Zhenyu
Depth Classification of Defects Based on Neural Architecture Search Journal Article
In: IEEE Access, vol. 9, pp. 73424-73432, 2021.
@article{9424564,
title = {Depth Classification of Defects Based on Neural Architecture Search},
author = {Haoze Chen and Zhijie Zhang and Chenyang Zhao and Jiaqi Liu and Wuliang Yin and Yanfeng Li and Fengxiang Wang and Chao Li and Zhenyu Lin},
url = {https://ieeexplore.ieee.org/abstract/document/9424564},
doi = {10.1109/ACCESS.2021.3077961},
year = {2021},
date = {2021-01-01},
journal = {IEEE Access},
volume = {9},
pages = {73424-73432},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1405.
Wei, Xun; Luo, Wang; Zhang, Xixi; Yang, Jie; Gui, Guan; Ohtsuki, Tomoaki
Differentiable Architecture Search-Based Automatic Modulation Classification Proceedings Article
In: 2021 IEEE Wireless Communications and Networking Conference (WCNC), pp. 1-6, 2021.
@inproceedings{9417449,
title = {Differentiable Architecture Search-Based Automatic Modulation Classification},
author = {Xun Wei and Wang Luo and Xixi Zhang and Jie Yang and Guan Gui and Tomoaki Ohtsuki},
url = {https://ieeexplore.ieee.org/abstract/document/9417449},
doi = {10.1109/WCNC49053.2021.9417449},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE Wireless Communications and Networking Conference (WCNC)},
pages = {1-6},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1404.
Chen, Shumei; Yu, Jianbo; Wang, Shijin
In: ISA Transactions, 2021, ISSN: 0019-0578.
@article{CHEN2021,
title = {One-dimensional convolutional neural network-based active feature extraction for fault detection and diagnosis of industrial processes and its understanding via visualization},
author = {Shumei Chen and Jianbo Yu and Shijin Wang},
url = {https://www.sciencedirect.com/science/article/pii/S0019057821002391},
doi = {https://doi.org/10.1016/j.isatra.2021.04.042},
issn = {0019-0578},
year = {2021},
date = {2021-01-01},
journal = {ISA Transactions},
abstract = {Feature extraction from process signals enables process monitoring models to be effective in industrial processes. Deep learning presents extensive possibilities for extracting abstract features from image and visual data. However, the main inputs of conventional deep neural networks are large images. To overcome this, a one-dimension convolution neural network-based model optimized by a reinforcement-learning-based neural architecture search, is proposed for multivariate processes control. The experimental results illustrate its predominance for detecting and recognizing process faults. Feature and network visualization are also implemented to explore the reasons for its outstanding performance. This research extends the applications of convolutional neural network based on one-dimension process signals in complex multivariate process control.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Feature extraction from process signals enables process monitoring models to be effective in industrial processes. Deep learning presents extensive possibilities for extracting abstract features from image and visual data. However, the main inputs of conventional deep neural networks are large images. To overcome this, a one-dimension convolution neural network-based model optimized by a reinforcement-learning-based neural architecture search, is proposed for multivariate processes control. The experimental results illustrate its predominance for detecting and recognizing process faults. Feature and network visualization are also implemented to explore the reasons for its outstanding performance. This research extends the applications of convolutional neural network based on one-dimension process signals in complex multivariate process control.
1403.
Liu, Mengyu; Yin, Hujun
Efficient pyramid context encoding and feature embedding for semantic segmentation Journal Article
In: Image and Vision Computing, vol. 111, pp. 104195, 2021, ISSN: 0262-8856.
@article{LIU2021104195,
title = {Efficient pyramid context encoding and feature embedding for semantic segmentation},
author = {Mengyu Liu and Hujun Yin},
url = {https://www.sciencedirect.com/science/article/pii/S0262885621001001},
doi = {https://doi.org/10.1016/j.imavis.2021.104195},
issn = {0262-8856},
year = {2021},
date = {2021-01-01},
journal = {Image and Vision Computing},
volume = {111},
pages = {104195},
abstract = {For reality applications of semantic segmentation, inference speed and memory usage are two important factors. To address these challenges, we propose a lightweight feature pyramid encoding network (FPENet) for semantic segmentation with a good trade-off between accuracy and speed. We use a series of feature pyramid encoding (FPE) blocks to encode context at multiple scales in the encoder. Each FPE block consists of different depthwise dilated convolutions that perform as a spatial pyramid to extract features and reduce computational costs. During training, a one-shot neural architecture search algorithm is adopted to find the optimal structure for each FPE block from a large search space with a small search cost. After the search for the encoder, a mutual embedding upsample module is introduced in the decoder, consisting of two attention blocks. The encoder-decoder attention mechanism is used to help aggregate efficiently high-level semantic features and low-level spatial details. The proposed network outperforms the existing real-time methods with fewer parameters and improved inference speed on the Cityscapes and CamVid benchmark datasets. Specifically, it achieved 72.3% mean IoU on the Cityscapes test set with only 0.4 M parameters and 192.6 FPS speed on an Nvidia Titan V100 GPU, and 73.4% mean IoU with 116.2 FPS when running on higher resolution images.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
For reality applications of semantic segmentation, inference speed and memory usage are two important factors. To address these challenges, we propose a lightweight feature pyramid encoding network (FPENet) for semantic segmentation with a good trade-off between accuracy and speed. We use a series of feature pyramid encoding (FPE) blocks to encode context at multiple scales in the encoder. Each FPE block consists of different depthwise dilated convolutions that perform as a spatial pyramid to extract features and reduce computational costs. During training, a one-shot neural architecture search algorithm is adopted to find the optimal structure for each FPE block from a large search space with a small search cost. After the search for the encoder, a mutual embedding upsample module is introduced in the decoder, consisting of two attention blocks. The encoder-decoder attention mechanism is used to help aggregate efficiently high-level semantic features and low-level spatial details. The proposed network outperforms the existing real-time methods with fewer parameters and improved inference speed on the Cityscapes and CamVid benchmark datasets. Specifically, it achieved 72.3% mean IoU on the Cityscapes test set with only 0.4 M parameters and 192.6 FPS speed on an Nvidia Titan V100 GPU, and 73.4% mean IoU with 116.2 FPS when running on higher resolution images.
1402.
Gao, Yanjie; Zhu, Yonghao; Zhang, Hongyu; Lin, Haoxiang; Yang, Mao
Resource-Guided Configuration Space Reduction for Deep Learning Models Proceedings Article
In: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), pp. 175-187, 2021.
@inproceedings{9402095,
title = {Resource-Guided Configuration Space Reduction for Deep Learning Models},
author = {Yanjie Gao and Yonghao Zhu and Hongyu Zhang and Haoxiang Lin and Mao Yang},
url = {https://ieeexplore.ieee.org/abstract/document/9402095},
doi = {10.1109/ICSE43902.2021.00028},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE)},
pages = {175-187},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1401.
Fei, Ke; Li, Qi; Cui, Can; chen, Xue; Xu, Xinxin; Xue, Benshan; Cai, Weifeng
Nontechnical Loss Detection using Neural Architecture Search and Outlier Detection Journal Article
In: E3S Web Conf., vol. 256, pp. 01025, 2021.
@article{refId0,
title = {Nontechnical Loss Detection using Neural Architecture Search and Outlier Detection},
author = {Ke} {Fei and Qi} {Li and Can} {Cui and Xue} {chen and Xinxin} {Xu and Benshan} {Xue and Weifeng} {Cai},
url = {https://doi.org/10.1051/e3sconf/202125601025},
doi = {10.1051/e3sconf/202125601025},
year = {2021},
date = {2021-01-01},
journal = {E3S Web Conf.},
volume = {256},
pages = {01025},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1400.
Wang, Xiaofang; Cao, Shengcao; Li, Mengtian; Kitani, Kris M
Neighborhood-Aware Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-06369,
title = {Neighborhood-Aware Neural Architecture Search},
author = {Xiaofang Wang and Shengcao Cao and Mengtian Li and Kris M Kitani},
url = {https://arxiv.org/abs/2105.06369},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.06369},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1399.
Chatzianastasis, Michail; Dasoulas, George; Siolas, Georgios; Vazirgiannis, Michalis
Operation Embeddings for Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-04885,
title = {Operation Embeddings for Neural Architecture Search},
author = {Michail Chatzianastasis and George Dasoulas and Georgios Siolas and Michalis Vazirgiannis},
url = {https://arxiv.org/abs/2105.04885},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.04885},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1398.
Huang, Han; Shen, Li; He, Chaoyang; Dong, Weisheng; Huang, Haozhi; Shi, Guangming
Lightweight Image Super-Resolution with Hierarchical and Differentiable Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-03939,
title = {Lightweight Image Super-Resolution with Hierarchical and Differentiable Neural Architecture Search},
author = {Han Huang and Li Shen and Chaoyang He and Weisheng Dong and Haozhi Huang and Guangming Shi},
url = {https://arxiv.org/abs/2105.03939},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.03939},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1397.
Fard, Farzaneh S; Tomar, Vikrant Singh
Expediting discovery in Neural Architecture Search by Combining Learning with Planning Proceedings Article
In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8373-8377, 2021.
@inproceedings{9413547,
title = {Expediting discovery in Neural Architecture Search by Combining Learning with Planning},
author = {Farzaneh S Fard and Vikrant Singh Tomar},
url = {https://ieeexplore.ieee.org/abstract/document/9413547},
doi = {10.1109/ICASSP39728.2021.9413547},
year = {2021},
date = {2021-01-01},
booktitle = {ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {8373-8377},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1396.
Hu, Yiming; Wang, Xingang; Li, Lujun; Gu, Qingyi
Improving One-Shot NAS with Shrinking-and-Expanding Supernet Journal Article
In: Pattern Recognition, vol. 118, pp. 108025, 2021, ISSN: 0031-3203.
@article{HU2021108025,
title = {Improving One-Shot NAS with Shrinking-and-Expanding Supernet},
author = {Yiming Hu and Xingang Wang and Lujun Li and Qingyi Gu},
url = {https://www.sciencedirect.com/science/article/pii/S0031320321002120},
doi = {https://doi.org/10.1016/j.patcog.2021.108025},
issn = {0031-3203},
year = {2021},
date = {2021-01-01},
journal = {Pattern Recognition},
volume = {118},
pages = {108025},
abstract = {Training a supernet using a copy of shared weights has become a popular approach to speed up neural architecture search (NAS). However, it is difficult for supernet to accurately evaluate on a large-scale search space due to high weight coupling in weight-sharing setting. To address this, we present a shrinking-and-expanding supernet that decouples the shared parameters by reducing the degree of weight sharing, avoiding unstable and inaccurate performance estimation as in previous methods. Specifically, we propose a new shrinking strategy that progressively simplifies the original search space by discarding unpromising operators in a smart way. Based on this, we further present an expanding strategy by appropriately increasing parameters of the shrunk supernet. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed method SE-NAS brings more accurate and more stable performance estimation. Experimental results on ImageNet dataset indicate that SE-NAS achieves higher Top-1 accuracy than its counterparts under the same complexity constraint and search space. The ablation study is presented to further understand SE-NAS.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Training a supernet using a copy of shared weights has become a popular approach to speed up neural architecture search (NAS). However, it is difficult for supernet to accurately evaluate on a large-scale search space due to high weight coupling in weight-sharing setting. To address this, we present a shrinking-and-expanding supernet that decouples the shared parameters by reducing the degree of weight sharing, avoiding unstable and inaccurate performance estimation as in previous methods. Specifically, we propose a new shrinking strategy that progressively simplifies the original search space by discarding unpromising operators in a smart way. Based on this, we further present an expanding strategy by appropriately increasing parameters of the shrunk supernet. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed method SE-NAS brings more accurate and more stable performance estimation. Experimental results on ImageNet dataset indicate that SE-NAS achieves higher Top-1 accuracy than its counterparts under the same complexity constraint and search space. The ablation study is presented to further understand SE-NAS.
1395.
Zhou, Yuan; Xie, Xukai; Kung, Sun-Yuan
Exploiting Operation Importance for Differentiable Neural Architecture Search Journal Article
In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1-14, 2021.
@article{9432795,
title = {Exploiting Operation Importance for Differentiable Neural Architecture Search},
author = {Yuan Zhou and Xukai Xie and Sun-Yuan Kung},
url = {https://ieeexplore.ieee.org/abstract/document/9432795},
doi = {10.1109/TNNLS.2021.3072950},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
pages = {1-14},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1394.
Malkova, Aleksandra; ï, Lo; Villien, Christophe; î, Beno; -, Massih
Self-Learning for Received Signal Strength Map Reconstruction with Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-07768,
title = {Self-Learning for Received Signal Strength Map Reconstruction with Neural Architecture Search},
author = {Aleksandra Malkova and Lo ï and Christophe Villien and Beno î and Massih -},
url = {https://arxiv.org/abs/2105.07768},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.07768},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1393.
Jin, Haifeng
Eficient Neural Architecture Search for Automated Deep Learning PhD Thesis
2021.
@phdthesis{JinPHD,
title = {Eficient Neural Architecture Search for Automated Deep Learning },
author = {Haifeng Jin },
url = {https://oaktrust.library.tamu.edu/bitstream/handle/1969.1/193093/JIN-DISSERTATION-2021.pdf?sequence=1&isAllowed=y},
year = {2021},
date = {2021-01-01},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
1392.
Yasarla, Rajeev; Joze, Hamid Reza Vaezi; Patel, Vishal M
Network Architecture Search for Face Enhancement Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-06528,
title = {Network Architecture Search for Face Enhancement},
author = {Rajeev Yasarla and Hamid Reza Vaezi Joze and Vishal M Patel},
url = {https://arxiv.org/abs/2105.06528},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.06528},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1391.
Rezaei, Seyed Saeed Changiz; Han, Fred X; Niu, Di; Salameh, Mohammad; Mills, Keith; Lian, Shuo; Lu, Wei; Jui, Shangling
Generative Adversarial Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-09356,
title = {Generative Adversarial Neural Architecture Search},
author = {Seyed Saeed Changiz Rezaei and Fred X Han and Di Niu and Mohammad Salameh and Keith Mills and Shuo Lian and Wei Lu and Shangling Jui},
url = {https://arxiv.org/abs/2105.09356},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.09356},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1390.
Sun, Ming; Dou, Haoxuan; Yan, Junjie
Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-08994,
title = {Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight},
author = {Ming Sun and Haoxuan Dou and Junjie Yan},
url = {https://arxiv.org/abs/2105.08994},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.08994},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1389.
Xu, Lumin; Guan, Yingda; Jin, Sheng; Liu, Wentao; Qian, Chen; Luo, Ping; Ouyang, Wanli; Wang, Xiaogang
ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-10154,
title = {ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search},
author = {Lumin Xu and Yingda Guan and Sheng Jin and Wentao Liu and Chen Qian and Ping Luo and Wanli Ouyang and Xiaogang Wang},
url = {https://arxiv.org/abs/2105.10154},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.10154},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1388.
O’Neill, Damien; Xue, Bing; Zhang, Mengjie
Evolutionary Neural Architecture Search for High-Dimensional Skip-Connection Structures on DenseNet Style Networks Journal Article
In: IEEE Transactions on Evolutionary Computation, pp. 1-1, 2021.
@article{9439793,
title = {Evolutionary Neural Architecture Search for High-Dimensional Skip-Connection Structures on DenseNet Style Networks},
author = {Damien O’Neill and Bing Xue and Mengjie Zhang},
url = {https://ieeexplore.ieee.org/abstract/document/9439793},
doi = {10.1109/TEVC.2021.3083315},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Evolutionary Computation},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1387.
Meng, Ze; Zhang, Jinnian; Li, Yumeng; Li, Jiancheng; Zhu, Tanchao; Sun, Lifeng
A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-10484,
title = {A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction},
author = {Ze Meng and Jinnian Zhang and Yumeng Li and Jiancheng Li and Tanchao Zhu and Lifeng Sun},
url = {https://arxiv.org/abs/2105.10484},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.10484},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1386.
Duan, Yawen; Chen, Xin; Xu, Hang; Chen, Zewei; Liang, Xiaodan; Zhang, Tong; Li, Zhenguo
TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search Proceedings Article
In: CVPR2021, 2021.
@inproceedings{DBLP:journals/corr/abs-2105-11871,
title = {TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search},
author = {Yawen Duan and Xin Chen and Hang Xu and Zewei Chen and Xiaodan Liang and Tong Zhang and Zhenguo Li},
url = {https://arxiv.org/abs/2105.11871},
year = {2021},
date = {2021-01-01},
booktitle = {CVPR2021},
journal = {CoRR},
volume = {abs/2105.11871},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1385.
Nguyen, Nam; -, Kwang
Quantum Embedding Search for Quantum Machine Learning Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-11853,
title = {Quantum Embedding Search for Quantum Machine Learning},
author = {Nam Nguyen and Kwang -},
url = {https://arxiv.org/abs/2105.11853},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.11853},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1384.
Lin, Yujun; Yang, Mengtian; Han, Song
NAAS: Neural Accelerator Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-13258,
title = {NAAS: Neural Accelerator Architecture Search},
author = {Yujun Lin and Mengtian Yang and Song Han},
url = {https://arxiv.org/abs/2105.13258},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.13258},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1383.
Maiti, Ritabrata; Agarwal, Priyanka; Kumar, Ragyayee Ravinder; Bhat, Aruna
Detection Of Skin Cancer Using Neural Architecture Search with Model Quantization Proceedings Article
In: 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), pp. 1807-1814, 2021.
@inproceedings{9432190,
title = {Detection Of Skin Cancer Using Neural Architecture Search with Model Quantization},
author = {Ritabrata Maiti and Priyanka Agarwal and Ragyayee Ravinder Kumar and Aruna Bhat},
url = {https://ieeexplore.ieee.org/abstract/document/9432190},
doi = {10.1109/ICICCS51141.2021.9432190},
year = {2021},
date = {2021-01-01},
booktitle = {2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS)},
pages = {1807-1814},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1382.
Ren, Yudan; Tao, Zeyang; Zhang, Wei; Liu, Tianming
Modeling Hierarchical Spatial and Temporal Patterns of Naturalistic fMRI Volume via Volumetric Deep Belief Network with Neural Architecture Search Proceedings Article
In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 130-134, 2021.
@inproceedings{9433811,
title = {Modeling Hierarchical Spatial and Temporal Patterns of Naturalistic fMRI Volume via Volumetric Deep Belief Network with Neural Architecture Search},
author = {Yudan Ren and Zeyang Tao and Wei Zhang and Tianming Liu},
url = {https://ieeexplore.ieee.org/abstract/document/9433811},
doi = {10.1109/ISBI48211.2021.9433811},
year = {2021},
date = {2021-01-01},
booktitle = {2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
pages = {130-134},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
1381.
Li, Shiqian; Li, Wei; Wen, Shiping; Shi, Kaibo; Yang, Yin; Zhou, Pan; Huang, Tingwen
Auto-FERNet: A Facial Expression Recognition Network with Architecture Search Journal Article
In: IEEE Transactions on Network Science and Engineering, pp. 1-1, 2021.
@article{9442348,
title = {Auto-FERNet: A Facial Expression Recognition Network with Architecture Search},
author = {Shiqian Li and Wei Li and Shiping Wen and Kaibo Shi and Yin Yang and Pan Zhou and Tingwen Huang},
doi = {10.1109/TNSE.2021.3083739},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Network Science and Engineering},
pages = {1-1},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1380.
Philipp, George
The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-12210,
title = {The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design},
author = {George Philipp},
url = {https://arxiv.org/abs/2105.12210},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.12210},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1379.
Yao, Lewei; Pi, Renjie; Xu, Hang; Zhang, Wei; Li, Zhenguo; Zhang, Tong
Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-12971,
title = {Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation},
author = {Lewei Yao and Renjie Pi and Hang Xu and Wei Zhang and Zhenguo Li and Tong Zhang},
url = {https://arxiv.org/abs/2105.12971},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.12971},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1378.
Zhou, Qinqin; Zhong, Bineng; Liu, Xin; Ji, Rongrong
Attention-Based Neural Architecture Search for Person Re-Identification Journal Article
In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1-13, 2021.
@article{9444559,
title = {Attention-Based Neural Architecture Search for Person Re-Identification},
author = {Qinqin Zhou and Bineng Zhong and Xin Liu and Rongrong Ji},
url = {https://ieeexplore.ieee.org/abstract/document/9444559},
doi = {10.1109/TNNLS.2021.3082701},
year = {2021},
date = {2021-01-01},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
pages = {1-13},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
1377.
Xu, Jin; Tan, Xu; Luo, Renqian; Song, Kaitao; Li, Jian; Qin, Tao; -, Tie
NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search Technical Report
2021.
@techreport{DBLP:journals/corr/abs-2105-14444,
title = {NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search},
author = {Jin Xu and Xu Tan and Renqian Luo and Kaitao Song and Jian Li and Tao Qin and Tie -},
url = {https://arxiv.org/abs/2105.14444},
year = {2021},
date = {2021-01-01},
journal = {CoRR},
volume = {abs/2105.14444},
keywords = {},
pubstate = {published},
tppubtype = {techreport}
}
1376.
Lin, Haojia; Wu, Shangbin; Chen, Yiping; Li, Wen; Luo, Zhipeng; Guo, Yulan; Wang, Cheng; Li, Jonathan
Semantic segmentation of 3D indoor LiDAR point clouds through feature pyramid architecture search Journal Article
In: ISPRS Journal of Photogrammetry and Remote Sensing, vol. 177, pp. 279-290, 2021, ISSN: 0924-2716.
@article{LIN2021279,
title = {Semantic segmentation of 3D indoor LiDAR point clouds through feature pyramid architecture search},
author = {Haojia Lin and Shangbin Wu and Yiping Chen and Wen Li and Zhipeng Luo and Yulan Guo and Cheng Wang and Jonathan Li},
url = {https://www.sciencedirect.com/science/article/pii/S0924271621001349},
doi = {https://doi.org/10.1016/j.isprsjprs.2021.05.009},
issn = {0924-2716},
year = {2021},
date = {2021-01-01},
journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
volume = {177},
pages = {279-290},
abstract = {Semantic segmentation of 3D Light Detection and Ranging (LiDAR) indoor point clouds using deep learning has been an active topic in recent years. However, most deep neural networks on point clouds conduct multi-level feature fusion via a simple U-shape architecture, which lacks enough capacity on both classification and localization in the segmentation task. In this paper, we propose a Neural Architecture Search (NAS) method to search a Feature Pyramid Network (FPN) module for 3D indoor point cloud semantic segmentation. Specifically, we aim to automatically find an effective feature pyramid architecture as a feature fusion neck in a designed novel pyramidal search space covering all information communication paths for multi-level features. The searched FPN module, named SFPN, contains the most important connections among all the potential paths to fuse representations at different levels. Our proposed SFPN is generic and effective as well as capable to be added to existing segmentation networks to augment the segmentation performance. Extensive experiments on ScanNet and S3DIS show that consistent and remarkable gains of segmentation performance can be achieved by different classical networks combined with SFPN. Specially, PointNet++-SFPN achieves mIoU gains of 7.8% on ScanNet v2 and 4.7% on S3DIS, and PointConv-SFPN achieves 4.5% and 3.7% improvement respectively on the above datasets.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Semantic segmentation of 3D Light Detection and Ranging (LiDAR) indoor point clouds using deep learning has been an active topic in recent years. However, most deep neural networks on point clouds conduct multi-level feature fusion via a simple U-shape architecture, which lacks enough capacity on both classification and localization in the segmentation task. In this paper, we propose a Neural Architecture Search (NAS) method to search a Feature Pyramid Network (FPN) module for 3D indoor point cloud semantic segmentation. Specifically, we aim to automatically find an effective feature pyramid architecture as a feature fusion neck in a designed novel pyramidal search space covering all information communication paths for multi-level features. The searched FPN module, named SFPN, contains the most important connections among all the potential paths to fuse representations at different levels. Our proposed SFPN is generic and effective as well as capable to be added to existing segmentation networks to augment the segmentation performance. Extensive experiments on ScanNet and S3DIS show that consistent and remarkable gains of segmentation performance can be achieved by different classical networks combined with SFPN. Specially, PointNet++-SFPN achieves mIoU gains of 7.8% on ScanNet v2 and 4.7% on S3DIS, and PointConv-SFPN achieves 4.5% and 3.7% improvement respectively on the above datasets.