The Heterogeneity Hypothesis: Finding Layer-Wise Dissimilated Network Architecture

In this paper, we tackle the problem of convolutional neural network design. Instead of focusing on the overall architecture design, we investigate a design space that is usually overlooked, \ie adjusting the channel configurations of predefined networks. We find that this adjustment can be achieved by pruning widened baseline networks and leads to superior performance. Base on that, we articulate the ``heterogeneity hypothesis'': with the same training protocol, there exists a layer-wise dissimilated network architecture (LW-DNA) that can outperform the original network with regular channel configurations under lower level of model complexity. The LW-DNA models are identified without added computational cost and training time compared with the original network. This constraint leads to controlled experiment which directs the focus to the importance of layer-wise specific channel configurations. Multiple sources of hints relate the benefits of LW-DNA models to overfitting, \ie the relative relationship between model complexity and dataset size. Experiments are conducted on various networks and datasets for image classification, visual tracking and image restoration. The resultant LW-DNA models consistently outperform the compared baseline models.

[1]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[3]  Dongwoo Lee,et al.  Joint Blind Motion Deblurring and Depth Estimation of Light Field , 2017, ECCV.

[4]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[5]  Philip H. S. Torr,et al.  A Signal Propagation Perspective for Pruning Neural Networks at Initialization , 2019, ICLR.

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

[7]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[8]  Kaiming He,et al.  Designing Network Design Spaces , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[10]  Luc Van Gool,et al.  Learning Discriminative Model Prediction for Tracking , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Xiangyu Zhang,et al.  MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[12]  Narendra Ahuja,et al.  Single image super-resolution from transformed self-exemplars , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[14]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

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

[16]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[17]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

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

[19]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

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

[21]  Philip H. S. Torr,et al.  SNIP: Single-shot Network Pruning based on Connection Sensitivity , 2018, ICLR.

[22]  Fan Yang,et al.  LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[24]  Bo Chen,et al.  NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications , 2018, ECCV.

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

[26]  Bernard Ghanem,et al.  TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild , 2018, ECCV.

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

[28]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.

[29]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

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

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

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

[33]  Luc Van Gool,et al.  Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[35]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Training Pruned Neural Networks , 2018, ArXiv.

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

[37]  Mingjie Sun,et al.  Rethinking the Value of Network Pruning , 2018, ICLR.

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

[39]  Luc Van Gool,et al.  DHP: Differentiable Meta Pruning via HyperNetworks , 2020, ECCV.

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

[41]  Aline Roumy,et al.  Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding , 2012, BMVC.

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

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