Robust Ensemble Person Re-Identification via Orthogonal Fusion with Occlusion Handling

arXiv:2404.00107v1 Announce Type: new
Abstract: Occlusion remains one of the major challenges in person reidentification (ReID) as a result of the diversity of poses and the variation of appearances. Developing novel architectures to improve the robustness of occlusion-aware person Re-ID requires new insights, especially on low-resolution edge cameras. We propose a deep ensemble model that harnesses both CNN and Transformer architectures to generate robust feature representations. To achieve robust Re-ID without the need to manually label occluded regions, we propose …

abstract architectures arxiv cameras challenges cs.ai cs.cv diversity edge ensemble fusion identification insights low major novel person resolution robust robustness type variation via