Hazy Re-ID: An Interference Suppression Model For Domain Adaptation Person Re-identification Under Inclement Weather Condition

TL;DR

This paper introduces a novel interference suppression model for person re-identification under hazy weather conditions, effectively reducing interference from weather effects in domain adaptation scenarios.

Contribution

The paper proposes a new Interference Suppression Model using teacher-student architecture and a discriminator to improve re-ID performance under adverse weather conditions.

Findings

Achieves superior performance on synthetic datasets

Effectively reduces weather-related interference in feature representations

Outperforms state-of-the-art methods in hazy weather scenarios

Abstract

In a conventional domain adaptation person Re-identification (Re-ID) task, both the training and test images in target domain are collected under the sunny weather. However, in reality, the pedestrians to be retrieved may be obtained under severe weather conditions such as hazy, dusty and snowing, etc. This paper proposes a novel Interference Suppression Model (ISM) to deal with the interference caused by the hazy weather in domain adaptation person Re-ID. A teacherstudent model is used in the ISM to distill the interference information at the feature level by reducing the discrepancy between the clear and the hazy intrinsic similarity matrix. Furthermore, in the distribution level, the extra discriminator is introduced to assist the student model make the interference feature distribution more clear. The experimental results show that the proposed method achieves the superior performance on two synthetic datasets than the stateof-the-art methods. The related code will be released online https://github.com/pangjian123/ISM-ReID.