Block Proposal Neural Architecture Search

The existing neural architecture search (NAS) methods usually restrict the search space to the pre-defined types of block for a fixed macro-architecture. However, this strategy will limit the search space and affect architecture flexibility if block proposal search (BPS) is not considered for NAS. As a result, block structure search is the bottleneck in many previous NAS works. In this work, we propose a new evolutionary algorithm referred to as latency EvoNAS (LEvoNAS) for block structure search, and also incorporate it to the NAS framework by developing a novel two-stage framework referred to as Block Proposal NAS (BP-NAS). Comprehensive experimental results on two computer vision tasks demonstrate the superiority of our newly proposed approach over the state-of-the-art lightweight methods. For the classification task on the ImageNet dataset, our BPN-A is better than 1.0-MobileNetV2 with similar latency, and our BPN-B saves 23.7% latency when compared with 1.4-MobileNetV2 with higher top-1 accuracy. Furthermore, for the object detection task on the COCO dataset, our method achieves significant performance improvement than MobileNetV2, which demonstrates the generalization capability of our newly proposed framework.

[1]  Mark Sandler,et al.  The Power of Sparsity in Convolutional Neural Networks , 2017, ArXiv.

[2]  Yali Amit,et al.  A Computational Model for Visual Selection , 1999, Neural Computation.

[3]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[4]  Xiaolin Hu,et al.  Accelerating convolutional neural networks by group-wise 2D-filter pruning , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[5]  Kurt Keutzer,et al.  Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[6]  Hichem Sahbi,et al.  Coarse-to-Fine Deep Kernel Networks , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[7]  Bo Chen,et al.  MnasNet: Platform-Aware Neural Architecture Search for Mobile , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Stan Z. Li,et al.  FloatBoost learning and statistical face detection , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Li Fei-Fei,et al.  Progressive Neural Architecture Search , 2017, ECCV.

[10]  Wei Wu,et al.  Practical Block-Wise Neural Network Architecture Generation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Hichem Sahbi,et al.  A Hierarchy of Support Vector Machines for Pattern Detection , 2006, J. Mach. Learn. Res..

[13]  Ramesh Raskar,et al.  Accelerating Neural Architecture Search using Performance Prediction , 2017, ICLR.

[14]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[16]  Yi Yang,et al.  Searching for a Robust Neural Architecture in Four GPU Hours , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[18]  Elliot Meyerson,et al.  Evolving Deep Neural Networks , 2017, Artificial Intelligence in the Age of Neural Networks and Brain Computing.

[19]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[20]  Xuesen Zhang,et al.  EcoNAS: Finding Proxies for Economical Neural Architecture Search , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Zhuowen Tu,et al.  Aggregated Residual Transformations for Deep Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Mark Sandler,et al.  MobileNetV2: Inverted Residuals and Linear Bottlenecks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[23]  Frank Hutter,et al.  Neural Architecture Search: A Survey , 2018, J. Mach. Learn. Res..

[24]  Bernhard Schölkopf,et al.  Improving the Accuracy and Speed of Support Vector Machines , 1996, NIPS.

[25]  Quoc V. Le,et al.  Understanding and Simplifying One-Shot Architecture Search , 2018, ICML.

[26]  Ramesh Raskar,et al.  Designing Neural Network Architectures using Reinforcement Learning , 2016, ICLR.

[27]  Kirthevasan Kandasamy,et al.  Neural Architecture Search with Bayesian Optimisation and Optimal Transport , 2018, NeurIPS.

[28]  Youhei Akimoto,et al.  Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search , 2019, ICML.

[29]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Frank Hutter,et al.  Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution , 2018, ICLR.

[31]  Kaiming He,et al.  Exploring Randomly Wired Neural Networks for Image Recognition , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[32]  Qingquan Song,et al.  Auto-Keras: An Efficient Neural Architecture Search System , 2018, KDD.

[33]  Alan L. Yuille,et al.  Genetic CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[34]  James M. Rehg,et al.  On the Design of Cascades of Boosted Ensembles for Face Detection , 2008, International Journal of Computer Vision.

[35]  Wei Wu,et al.  BlockQNN: Efficient Block-Wise Neural Network Architecture Generation , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[37]  Xiangyu Zhang,et al.  ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design , 2018, ECCV.

[38]  Song Han,et al.  ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware , 2018, ICLR.

[39]  Wei Wu,et al.  Improving One-Shot NAS by Suppressing the Posterior Fading , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[41]  Xiaogang Wang,et al.  Chained Cascade Network for Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[42]  Bernhard Schölkopf,et al.  Face Detection - Efficient and Rank Deficient , 2004, NIPS.

[43]  Yong Yu,et al.  Efficient Architecture Search by Network Transformation , 2017, AAAI.

[44]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[45]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.

[46]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[47]  Yuandong Tian,et al.  FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[48]  Quoc V. Le,et al.  Large-Scale Evolution of Image Classifiers , 2017, ICML.

[49]  Oriol Vinyals,et al.  Hierarchical Representations for Efficient Architecture Search , 2017, ICLR.

[50]  Quoc V. Le,et al.  Searching for MobileNetV3 , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[51]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Xiaopeng Zhang,et al.  PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search , 2020, ICLR.

[53]  Tie-Yan Liu,et al.  Neural Architecture Optimization , 2018, NeurIPS.

[54]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[55]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[56]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[57]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[58]  Vijay Vasudevan,et al.  Learning Transferable Architectures for Scalable Image Recognition , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[59]  Kai Chen,et al.  Hybrid Task Cascade for Instance Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[60]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[61]  Ameet Talwalkar,et al.  Random Search and Reproducibility for Neural Architecture Search , 2019, UAI.

[62]  Qi Tian,et al.  Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[63]  Gang Hua,et al.  A convolutional neural network cascade for face detection , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[64]  Hichem Sahbi,et al.  Face detection using coarse-to-fine support vector classifiers , 2002, Proceedings. International Conference on Image Processing.

[65]  Forrest N. Iandola,et al.  SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size , 2016, ArXiv.

[66]  Jian Sun,et al.  DetNAS: Backbone Search for Object Detection , 2019, NeurIPS.

[67]  Kilian Q. Weinberger,et al.  CondenseNet: An Efficient DenseNet Using Learned Group Convolutions , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[68]  Wei Wu,et al.  Computation Reallocation for Object Detection , 2019, ICLR.

[69]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[70]  Lu Sheng,et al.  Powering One-shot Topological NAS with Stabilized Share-parameter Proxy , 2020, ECCV.

[71]  Li Fei-Fei,et al.  Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).