Domain-adaptive Person Re-identification without Cross-camera Paired Samples

TL;DR

This paper introduces a novel domain-adaptive person re-identification method that effectively learns discriminative features across long-distance scenes without relying on cross-camera paired samples, addressing a key challenge in real-world applications.

Contribution

It proposes a new framework with CSCM and CCFLM modules, including a feature recombination mechanism and style transfer techniques, to improve cross-camera re-ID without paired samples.

Findings

Outperforms existing methods on three challenging datasets.

Effectively handles unpaired cross-camera samples.

Enhances feature discriminability and generalization ability.

Abstract

Existing person re-identification (re-ID) research mainly focuses on pedestrian identity matching across cameras in adjacent areas. However, in reality, it is inevitable to face the problem of pedestrian identity matching across long-distance scenes. The cross-camera pedestrian samples collected from long-distance scenes often have no positive samples. It is extremely challenging to use cross-camera negative samples to achieve cross-region pedestrian identity matching. Therefore, a novel domain-adaptive person re-ID method that focuses on cross-camera consistent discriminative feature learning under the supervision of unpaired samples is proposed. This method mainly includes category synergy co-promotion module (CSCM) and cross-camera consistent feature learning module (CCFLM). In CSCM, a task-specific feature recombination (FRT) mechanism is proposed. This mechanism first groups features according to their contributions to specific tasks. Then an interactive promotion learning (IPL) scheme between feature groups is developed and embedded in this mechanism to enhance feature discriminability. Since the control parameters of the specific task model are reduced after division by task, the generalization ability of the model is improved. In CCFLM, instance-level feature distribution alignment and cross-camera identity consistent learning methods are constructed. Therefore, the supervised model training is achieved under the style supervision of the target domain by exchanging styles between source-domain samples and target-domain samples, and the challenges caused by the lack of cross-camera paired samples are solved by utilizing cross-camera similar samples. In experiments, three challenging datasets are used as target domains, and the effectiveness of the proposed method is demonstrated through four experimental settings.