Weakly Supervised Person Search with Region Siamese Networks

TL;DR

This paper introduces a weakly supervised person search method using Region Siamese Networks that only requires bounding box annotations, achieving competitive results and surpassing some fully supervised methods.

Contribution

The paper proposes a novel weakly supervised framework for person search that eliminates the need for identity labels, using instance-level and cluster-level losses in a Siamese network architecture.

Findings

Achieves 87.1% rank-1 accuracy on CUHK-SYSU benchmark

Surpasses several fully supervised methods like OIM and MGTS

Demonstrates effectiveness of weak supervision with bounding boxes only

Abstract

Supervised learning is dominant in person search, but it requires elaborate labeling of bounding boxes and identities. Large-scale labeled training data is often difficult to collect, especially for person identities. A natural question is whether a good person search model can be trained without the need of identity supervision. In this paper, we present a weakly supervised setting where only bounding box annotations are available. Based on this new setting, we provide an effective baseline model termed Region Siamese Networks (R-SiamNets). Towards learning useful representations for recognition in the absence of identity labels, we supervise the R-SiamNet with instance-level consistency loss and cluster-level contrastive loss. For instance-level consistency learning, the R-SiamNet is constrained to extract consistent features from each person region with or without out-of-region context. For cluster-level contrastive learning, we enforce the aggregation of closest instances and the separation of dissimilar ones in feature space. Extensive experiments validate the utility of our weakly supervised method. Our model achieves the rank-1 of 87.1% and mAP of 86.0% on CUHK-SYSU benchmark, which surpasses several fully supervised methods, such as OIM and MGTS, by a clear margin. More promising performance can be reached by incorporating extra training data. We hope this work could encourage the future research in this field.