VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification
This addresses the challenge of accurately retrieving persons across cameras for surveillance applications, representing an incremental improvement over existing methods.
The paper tackled the problem of person re-identification by proposing a multi-receptive field attention module and view-specific mechanism to handle variations like background clutter and view conditions, achieving state-of-the-art results such as 95.5% rank-1 accuracy on Market-1501.
Person re-identification (re-ID) aims to retrieve the same person across different cameras. In practice, it still remains a challenging task due to background clutter, variations on body poses and view conditions, inaccurate bounding box detection, etc. To tackle these issues, in this paper, we propose a novel multi-receptive field attention (MRFA) module that utilizes filters of various sizes to help network focusing on informative pixels. Besides, we present a view-specific mechanism that guides attention module to handle the variation of view conditions. Moreover, we introduce a Gaussian horizontal random cropping/padding method which further improves the robustness of our proposed network. Comprehensive experiments demonstrate the effectiveness of each component. Our method achieves 95.5% / 88.1% in rank-1 / mAP on Market-1501, 88.9% / 80.0% on DukeMTMC-reID, 81.1% / 78.8% on CUHK03 labeled dataset and 78.9% / 75.3% on CUHK03 detected dataset, outperforming current state-of-the-art methods.