PersonMAE: Person Re-Identification Pre-Training with Masked AutoEncoders
원문 초록
Pre-training is playing an increasingly important role in learning generic feature representation for Person Re-identification (ReID). We argue that a high-quality ReID representation should have three properties, namely, multi-level awareness, occlusion robustness, and cross-region invariance. To this end, we propose a simple yet effective pre-training framework, namely PersonMAE, which involves two core designs into masked autoencoders to better serve the task of Person Re-ID. 1) PersonMAE generates two regions from the given image with RegionA as the input and \textit{RegionB} as the prediction target. RegionA is corrupted with block-wise masking to mimic common occlusion in ReID and its remaining visible parts are fed into the encoder. 2) Then PersonMAE aims to predict the whole RegionB at both pixel level and semantic feature level. It encourages its pre-trained feature representations with the three properties mentioned above. These properties make PersonMAE compatible with downstream Person ReID tasks, leading to state-of-the-art performance on four downstream ReID tasks, i.e., supervised (holistic and occluded setting), and unsupervised (UDA and USL setting). Notably, on the commonly adopted supervised setting, PersonMAE with ViT-B backbone achieves 79.8% and 69.5% mAP on the MSMT17 and OccDuke datasets, surpassing the previous state-of-the-art by a large margin of +8.0 mAP, and +5.3 mAP, respectively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID
Following the Clues: Experiments on Person Re-ID using Cross-Modal Intelligence
Domain Generalization for Person Re-identification: A Survey Towards Domain-Agnostic Person Matching
ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model
S3CE-Net: Spike-guided Spatiotemporal Semantic Coupling and Expansion Network for Long Sequence Event Re-Identification
Differentiable Channel Selection in Self-Attention For Person Re-Identification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.