Human Semantic Parsing for Person Re-identification
This work addresses the problem of distinguishing individuals across cameras for surveillance and security applications, offering a novel approach with substantial improvements over existing methods.
The paper tackles the challenge of person re-identification by integrating human semantic parsing to improve representation learning, achieving state-of-the-art performance with significant gains such as ~17% mAP on Market-1501 and ~24% mAP on DukeMTMC-reID.
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.