Adversarial Self-Attack Defense and Spatial-Temporal Relation Mining for Visible-Infrared Video Person Re-Identification

TL;DR

This paper introduces a novel approach for visible-infrared video person re-identification that combines adversarial self-attack defense with spatial-temporal relation mining to improve robustness against complex scene variations.

Contribution

It proposes a unified framework integrating adversarial self-attack defense with spatial-temporal relation mining for more robust cross-modal person re-ID.

Findings

Achieves superior performance on large-scale cross-modality video datasets.

Effectively enhances model robustness against scene and modality variations.

Introduces a novel adversarial self-attack mechanism without generating adversarial samples.

Abstract

In visible-infrared video person re-identification (re-ID), extracting features not affected by complex scenes (such as modality, camera views, pedestrian pose, background, etc.) changes, and mining and utilizing motion information are the keys to solving cross-modal pedestrian identity matching. To this end, the paper proposes a new visible-infrared video person re-ID method from a novel perspective, i.e., adversarial self-attack defense and spatial-temporal relation mining. In this work, the changes of views, posture, background and modal discrepancy are considered as the main factors that cause the perturbations of person identity features. Such interference information contained in the training samples is used as an adversarial perturbation. It performs adversarial attacks on the re-ID model during the training to make the model more robust to these unfavorable factors. The attack from the adversarial perturbation is introduced by activating the interference information contained in the input samples without generating adversarial samples, and it can be thus called adversarial self-attack. This design allows adversarial attack and defense to be integrated into one framework. This paper further proposes a spatial-temporal information-guided feature representation network to use the information in video sequences. The network cannot only extract the information contained in the video-frame sequences but also use the relation of the local information in space to guide the network to extract more robust features. The proposed method exhibits compelling performance on large-scale cross-modality video datasets. The source code of the proposed method will be released at https://github.com/lhf12278/xxx.