Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification

TL;DR

This paper introduces a multi-scale, context-aware deep network that learns both full-body and deformable body parts for person re-identification, significantly improving accuracy on challenging datasets.

Contribution

It proposes a novel multi-scale network with deformable part localization using Spatial Transformer Networks, enhancing feature robustness for person ReID.

Findings

Achieves state-of-the-art results on Market1501, CUHK03, and MARS datasets.

Effectively handles pose variations and background clutter.

Outperforms existing methods in person re-identification accuracy.

Abstract

Person Re-identification (ReID) is to identify the same person across different cameras. It is a challenging task due to the large variations in person pose, occlusion, background clutter, etc How to extract powerful features is a fundamental problem in ReID and is still an open problem today. In this paper, we design a Multi-Scale Context-Aware Network (MSCAN) to learn powerful features over full body and body parts, which can well capture the local context knowledge by stacking multi-scale convolutions in each layer. Moreover, instead of using predefined rigid parts, we propose to learn and localize deformable pedestrian parts using Spatial Transformer Networks (STN) with novel spatial constraints. The learned body parts can release some difficulties, eg pose variations and background clutters, in part-based representation. Finally, we integrate the representation learning processes of full body and body parts into a unified framework for person ReID through multi-class person identification tasks. Extensive evaluations on current challenging large-scale person ReID datasets, including the image-based Market1501, CUHK03 and sequence-based MARS datasets, show that the proposed method achieves the state-of-the-art results.