Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
This work addresses the challenge of capturing useful contextual cues beyond predefined human parts in person re-identification, which is incremental as it builds on existing methods by integrating human parsing and self-attention.
The paper tackles the problem of missed contextual cues in person re-identification by exploiting both accurate human parts and coarse non-human parts, achieving new state-of-the-art performances on three benchmarks: Market-1501, DukeMTMC-reID, and CUHK03.
Person re-identification is a challenging task due to various complex factors. Recent studies have attempted to integrate human parsing results or externally defined attributes to help capture human parts or important object regions. On the other hand, there still exist many useful contextual cues that do not fall into the scope of predefined human parts or attributes. In this paper, we address the missed contextual cues by exploiting both the accurate human parts and the coarse non-human parts. In our implementation, we apply a human parsing model to extract the binary human part masks \emph{and} a self-attention mechanism to capture the soft latent (non-human) part masks. We verify the effectiveness of our approach with new state-of-the-art performances on three challenging benchmarks: Market-1501, DukeMTMC-reID and CUHK03. Our implementation is available at https://github.com/ggjy/P2Net.pytorch.