Accelerating Very Deep Convolutional Networks for Classification and Detection
Xiangyu Zhang, Jianhua Zou, Kaiming He et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2015
This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs [1] that have substantially impacted the computer vision community. Unlike previous methods that are designed for approximating linear filters or linear responses, our method takes the nonlinear units into account. We develop an effective solution to the resulting nonlinear optimization problem without the need of stochastic gradient descent (SGD). More importantly, while previous methods mainly focus on optimizing one or two layers, our nonlinear method enables an asymmetric reconstruction that reduces the rapidly accumulated error when multiple (e.g., ≥ 10) layers are approximated. For the widely used very deep VGG-16 model [1] , our method achieves a whole-model speedup of 4 × with merely a 0.3 percent increase of top-5 error in ImageNet classification. Our 4 × accelerated VGG-16 model also shows a graceful accuracy degradation for object detection when plugged into the Fast R-CNN detector [2] .
Cited by 832 works. doi:10.1109/tpami.2015.2502579 Open-access PDF
Authors
References
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Matrix Computations
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Going deeper with convolutions
- ImageNet Large Scale Visual Recognition Challenge
- Backpropagation Applied to Handwritten Zip Code Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Fully convolutional networks for semantic segmentation
- Caffe