Can I read BiRe-ID: Binary Neural Network for Efficient Person Re-ID on EtoBox?

BiRe-ID: Binary Neural Network for Efficient Person Re-ID by Sheng Xu; Chang Liu; Baochang Zhang; Jinhu Lü; Guodong Guo; David Doermann is a Computer Science article available to read on EtoBox.

What is BiRe-ID: Binary Neural Network for Efficient Person Re-ID about?

Person re-identification (Re-ID) has been promoted by the significant success of convolutional neural networks (CNNs). However, the application of such CNN-based Re-ID methods depends on the tremendous consumption of computation and memory resources, which affects its development on resource-limited devices such as next generation AI chips. As a result, CNN binarization has attracted increasing attention, which leads to binary neural networks (BNNs). In this article, we propose a new BNN-based framework for efficient person Re-ID (BiRe-ID). In this work, we discover that the significant performance drop of binarized models for Re-ID task is caused by the degraded representation capacity of kernels and features. To address the issues, we propose the kernel and feature refinement based on generative adversarial learning (KR-GAL and FR-GAL) to enhance the representation capacity of BNNs. We first introduce an adversarial attention mechanism to refine the binarized kernels based on their real-valued counterparts. Specifically, we introduce a scale factor to restore the scale of 1-bit convolution. And we employ an effective generative adversarial learning method to train the attention-a

Who reads BiRe-ID: Binary Neural Network for Efficient Person Re-ID?

Author

Sheng Xu; Chang Liu; Baochang Zhang; Jinhu Lü; Guodong Guo; David Doermann

Publisher

Association for Computing Machinery (ACM)

Published

2022

Language

EN

Field

Computer Science (Physical Sciences)