Deep Network Pruning for Object Detection

With the increasing success of deep learning in various applications, there is an increasing need to have deep models that can be used for deployment in real-time and/or resource constrained scenarios. In this context, this paper analyzes the pruning of deep models for object detection in order to reduce the number of weights and hence the number of computations. Very deep networks based on ResNet like architectures, like YOLOv3 have unique challenges when attempting to prune them. This paper proposes a network pruning technique based on agglomerative clustering for the feature extractor and using mutual information for the detector. The performance of the proposed techniques is also compared with that of a relatively shallow network, i.e., YOLOv2. A compression percentage of around 30% results in a 10% drop of mean average precision (mAP) in YOLOv3, whereas in YOLOv2 the drop was around 6% on the COCO dataset.

[1]  Nikos Komodakis,et al.  Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer , 2016, ICLR.

[2]  Huchuan Lu,et al.  Deep Mutual Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[4]  Babak Hassibi,et al.  Second Order Derivatives for Network Pruning: Optimal Brain Surgeon , 1992, NIPS.

[5]  Vincent Vanhoucke,et al.  Improving the speed of neural networks on CPUs , 2011 .

[6]  Jian Cheng,et al.  Quantized Convolutional Neural Networks for Mobile Devices , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[8]  Yiran Chen,et al.  Learning Structured Sparsity in Deep Neural Networks , 2016, NIPS.

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

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

[11]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Victor S. Lempitsky,et al.  Fast ConvNets Using Group-Wise Brain Damage , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  R. Venkatesh Babu,et al.  Data-free Parameter Pruning for Deep Neural Networks , 2015, BMVC.

[14]  Pritish Narayanan,et al.  Deep Learning with Limited Numerical Precision , 2015, ICML.

[15]  Honglak Lee,et al.  Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units , 2016, ICML.

[16]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[17]  Ivan V. Oseledets,et al.  Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition , 2014, ICLR.

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

[19]  Hao Zhou,et al.  Less Is More: Towards Compact CNNs , 2016, ECCV.

[20]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

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

[22]  Lei Zhou,et al.  Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression , 2018, ArXiv.

[23]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.