Performance Guaranteed Network Acceleration via High-Order Residual Quantization

Abstract

Input binarization has shown to be an effective way for network acceleration. However, previous binarization scheme could be regarded as simple pixel-wise thresholding operations (i.e., order-one approximation) and suffers a big accuracy loss. In this paper, we propose a highorder binarization scheme, which achieves more accurate approximation while still possesses the advantage of binary operation. In particular, the proposed scheme recursively performs residual quantization and yields a series of binary input images with decreasing magnitude scales. Accordingly, we propose high-order binary filtering and gradient propagation operations for both forward and backward computations. Theoretical analysis shows approximation error guarantee property of proposed method. Extensive experimental results demonstrate that the proposed scheme yields great recognition accuracy while being accelerated.

9 pages, 8 figures, Proceeding of IEEE International Conference on Computer Vision 2017

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Spatially-sparse convolutional neural networks
• Memory Bounded Deep Convolutional Networks
• Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation