End-to-End Comparative Attention Networks for Person Re-identification

TL;DR

This paper introduces an end-to-end comparative attention network that selectively focuses on discriminative parts of person images to improve re-identification accuracy across camera views, outperforming existing methods.

Contribution

The novel end-to-end CAN model employs soft attention to adaptively compare local regions of person images, enhancing re-identification performance over prior approaches.

Findings

Outperforms baseline methods on CUHK01, CHUHK03, and Market-1501 datasets.

Achieves state-of-the-art accuracy in person re-identification.

Effectively learns to focus on relevant image parts for identification.

Abstract

Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance. In this paper, we propose a new soft attention based model, i.e., the end to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on three benchmark person re-identification datasets, including CUHK01, CHUHK03 and Market-1501, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.