Learning Channel-Wise Interactions for Binary Convolutional Neural Networks

In this paper, we propose a channel-wise interaction based binary convolutional neural network learning method (CI-BCNN) for efficient inference. Conventional methods apply xnor and bitcount operations in binary convolution with notable quantization error, which usually obtains inconsistent signs in binary feature maps compared with their full-precision counterpart and leads to significant information loss. In contrast, our CI-BCNN mines the channel-wise interactions, through which prior knowledge is provided to alleviate inconsistency of signs in binary feature maps and preserves the information of input samples during inference. Specifically, we mine the channel-wise interactions by a reinforcement learning model, and impose channel-wise priors on the intermediate feature maps through the interacted bitcount function. Extensive experiments on the CIFAR-10 and ImageNet datasets show that our method outperforms the state-of-the-art binary convolutional neural networks with less computational and storage cost.

[1]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Dacheng Tao,et al.  On Compressing Deep Models by Low Rank and Sparse Decomposition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[4]  Wei Liu,et al.  Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm , 2018, ECCV.

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

[6]  Jiwen Lu,et al.  Learning Globally Optimized Object Detector via Policy Gradient , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Xin Wang,et al.  Deep Reinforcement Learning for Visual Object Tracking in Videos , 2017, ArXiv.

[9]  Simon Lucey,et al.  Learning Policies for Adaptive Tracking with Deep Feature Cascades , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Seunghoon Hong,et al.  Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network , 2015, ICML.

[11]  Yoshua Bengio,et al.  BinaryConnect: Training Deep Neural Networks with binary weights during propagations , 2015, NIPS.

[12]  Igor Carron,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016 .

[13]  Jian Sun,et al.  Deep Learning with Low Precision by Half-Wave Gaussian Quantization , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Ira Kemelmacher-Shlizerman,et al.  Level Playing Field for Million Scale Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Misha Denil,et al.  Predicting Parameters in Deep Learning , 2014 .

[16]  Deva Ramanan,et al.  Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[17]  Dongqing Zhang,et al.  Neural Aggregation Network for Video Face Recognition , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[19]  Luca Bertinetto,et al.  Fully-Convolutional Siamese Networks for Object Tracking , 2016, ECCV Workshops.

[20]  Dacheng Tao,et al.  Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Joan Bruna,et al.  Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation , 2014, NIPS.

[22]  Hanan Samet,et al.  Pruning Filters for Efficient ConvNets , 2016, ICLR.

[23]  Cristian Sminchisescu,et al.  Deep Reinforcement Learning of Region Proposal Networks for Object Detection , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[24]  Xiangyu Zhang,et al.  Channel Pruning for Accelerating Very Deep Neural Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[25]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[26]  Max Welling,et al.  Bayesian Compression for Deep Learning , 2017, NIPS.

[27]  Max Welling,et al.  Soft Weight-Sharing for Neural Network Compression , 2017, ICLR.

[28]  Bohyung Han,et al.  Learning Multi-domain Convolutional Neural Networks for Visual Tracking , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[30]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[31]  Philip Heng Wai Leong,et al.  SYQ: Learning Symmetric Quantization for Efficient Deep Neural Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  G. Hua,et al.  LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks , 2018, ECCV.

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

[34]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, ArXiv.

[35]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[36]  Jin Young Choi,et al.  Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[38]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[39]  James T. Kwok,et al.  Loss-aware Binarization of Deep Networks , 2016, ICLR.

[40]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[41]  Jian Sun,et al.  Accelerating Very Deep Convolutional Networks for Classification and Detection , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Song Han,et al.  Trained Ternary Quantization , 2016, ICLR.

[43]  Wei Pan,et al.  Towards Accurate Binary Convolutional Neural Network , 2017, NIPS.