A Semantic Controllable Self-Supervised Learning Framework to learn general human representations from massive unlabeled human images, which can benefit downstream human-centric tasks to the maximum extent
Were the feature embedding sizes defined here used for your person ReID experiments link, i.e., 96 for Swin Tiny, 96 for Swin Small, and 128 for Swin Base? Or did you use embeddings of higher dimension? It was not mentioned in the paper. Thanks.
cwhgn
commented
1 year ago
Were the feature embedding sizes defined here used for your person ReID experiments link, i.e., 96 for Swin Tiny, 96 for Swin Small, and 128 for Swin Base? Or did you use embeddings of higher dimension? It was not mentioned in the paper. Thanks.