English

STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification

Computer Vision and Pattern Recognition 2021-08-20 v3

Abstract

Recently, Batch DropBlock network (BDB) has demonstrated its effectiveness on person image representation and re-identification task via feature erasing. However, BDB drops the features \textbf{randomly} which may lead to sub-optimal results. In this paper, we propose a novel Self-Thresholding attention guided Adaptive DropBlock network (STADB) for person re-ID which can \textbf{adaptively} erase the most discriminative regions. Specifically, STADB first obtains an attention map by channel-wise pooling and returns a drop mask by thresholding the attention map. Then, the input features and self-thresholding attention guided drop mask are multiplied to generate the dropped feature maps. In addition, STADB utilizes the spatial and channel attention to learn a better feature map and iteratively trains the feature dropping module for person re-ID. Experiments on several benchmark datasets demonstrate that the proposed STADB outperforms many other related methods for person re-ID. The source code of this paper is released at: \textcolor{red}{\url{https://github.com/wangxiao5791509/STADB_ReID}}.

Keywords

Cite

@article{arxiv.2007.03584,
  title  = {STADB: A Self-Thresholding Attention Guided ADB Network for Person Re-identification},
  author = {Bo Jiang and Sheng Wang and Xiao Wang and Aihua Zheng},
  journal= {arXiv preprint arXiv:2007.03584},
  year   = {2021}
}
R2 v1 2026-06-23T16:55:29.561Z