Human Semantic Parsing for Person Re-identification

TL;DR

This paper introduces a human semantic parsing approach for person re-identification, significantly improving accuracy by leveraging pixel-level human part modeling and a simple training strategy with standard deep architectures.

Contribution

It proposes using human semantic parsing for person re-identification, achieving state-of-the-art results without modifying existing deep models.

Findings

Outperforms baseline methods on multiple datasets.

Achieves ~17% improvement in mAP on Market-1501.

Enhances rank-1 accuracy by ~6% on Market-1501.

Abstract

Person re-identification is a challenging task mainly due to factors such as background clutter, pose, illumination and camera point of view variations. These elements hinder the process of extracting robust and discriminative representations, hence preventing different identities from being successfully distinguished. To improve the representation learning, usually, local features from human body parts are extracted. However, the common practice for such a process has been based on bounding box part detection. In this paper, we propose to adopt human semantic parsing which, due to its pixel-level accuracy and capability of modeling arbitrary contours, is naturally a better alternative. Our proposed SPReID integrates human semantic parsing in person re-identification and not only considerably outperforms its counter baseline, but achieves state-of-the-art performance. We also show that by employing a \textit{simple} yet effective training strategy, standard popular deep convolutional architectures such as Inception-V3 and ResNet-152, with no modification, while operating solely on full image, can dramatically outperform current state-of-the-art. Our proposed methods improve state-of-the-art person re-identification on: Market-1501 by ~17% in mAP and ~6% in rank-1, CUHK03 by ~4% in rank-1 and DukeMTMC-reID by ~24% in mAP and ~10% in rank-1.