Feb, 2024
针对弱监督式人员再识别的对比式多实例学习
Contrastive Multiple Instance Learning for Weakly Supervised Person ReID
Jacob Tyo, Zachary C. Lipton
TL;DRContrastive Multiple Instance Learning (CMIL) is a novel framework for weakly supervised person re-identification that leverages contrastive losses to enhance performance, achieving state-of-the-art results on large-scale datasets without pseudo labels and surpassing baselines on multiple datasets.