RotateConv: Making Asymmetric Convolutional Kernels Rotatable

In deep Convolutional Neural Networks(CNN), the design of kernel shapes influences a lot on the model size and performance. In this work, our proposed method, RotateConv, applies a novel kernel shape to massively reduce the number of parameters while maintaining considerable performance. The new shape is extremely simple as a line segment one, and we equip it with the rotatable ability which aims to learn diverse features with respect to different angles. The kernel weights and angles are learned simultaneously during end-to-end training via the standard back-propagation algorithm. There are two variants of RotateConv that only have 2 and 4 parameters respectively depending on whether using weight sharing, which are much compressed than the normal $3\times 3$ kernel with 9 parameters. In experiments, we validate our RotateConv with two classical models, ResNet and DenseNet, on four image classification benchmark datasets, namely MNIST, CIFAR10, CIFAR100 and SVHN.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Andrew Zisserman,et al.  Speeding up Convolutional Neural Networks with Low Rank Expansions , 2014, BMVC.

[3]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

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

[6]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[8]  Wei Wang,et al.  Irregular Convolutional Neural Networks , 2017, 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR).

[9]  Yi Li,et al.  Deformable Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[10]  Bin Liu,et al.  Ternary Weight Networks , 2016, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[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]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[14]  Eriko Nurvitadhi,et al.  Accelerating Deep Convolutional Networks using low-precision and sparsity , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

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

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

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

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

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

[21]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[23]  D. Gabor,et al.  Theory of communication. Part 1: The analysis of information , 1946 .

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

[25]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

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

[27]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Ali Farhadi,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016, ECCV.

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