Occluded Person Re-Identification via Defending Against Attacks From Obstacles

Due to incomplete appearance features, the identity matching of occluded pedestrians under multiple cross-camera views is a long-term challenge. Although existing re-identification (re-ID) solutions of occluded pedestrians have made significant progress, most of them achieve accurate identity matching by extracting pedestrian appearance features from unoccluded areas. However, when a pedestrian is partially blocked by the body of another pedestrian, existing methods cannot accurately determine whether the unoccluded body parts belong to the target pedestrian, which brings great difficulties to pedestrian identity matching. To alleviate this problem, this paper introduces the idea of adversarial attack into occluded person re-ID and proposes an adversarial training framework that can defend against attacks from obstacles to resist the interference of obstacles on pedestrian identity matching. Unlike existing solutions, the proposed framework is not limited to extracting features of unoccluded human body areas to achieve occluded person re-ID, but explores how to make the re-ID model more resistant to obstacles. In the proposed framework, the occluded pedestrian images are regarded as adversarial examples and used to attack model training. If the trained model can defend against this kind of attack, its generalization is significantly improved, and the above-mentioned issues are also effectively solved. Specifically, a single-branch dual-stream collaborative network is designed. With the cooperation of the pre-trained verification guidance network, the model realizes the attack and defense of adversarial samples. This work broadens research horizons in robust model design of occluded person re-ID, and expands the scope of adversarial attacks. Compared with existing solutions, a lot of experimental results confirm that the proposed solution achieves better performance on two occluded re-ID datasets and two partial re-ID datasets.