Re-identify people with only bounding box annotations by spatial and occlusion contrasts with DICL
Re-identify people with only bounding box annotations by spatial and occlusion contrasts with DICL
Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search
arXiv paper abstract https://arxiv.org/abs/2302.04607
arXiv PDF paper https://arxiv.org/pdf/2302.04607.pdf
GitHub https://github.com/jiabeiwangtju/dicl
Weakly supervised person search aims to perform joint pedestrian detection and re-identification (re-id) with only person bounding-box annotations.
… present a novel deep intra-image contrastive learning using a Siamese network.
Two key modules are spatial-invariant contrast (SIC) and occlusion-invariant contrast (OIC).
SIC performs many-to-one contrasts between two branches of Siamese network and … learn discriminative scale-invariant and location-invariant features to solve spatial-level variance.
OIC enhances feature consistency with the masking strategy to learn occlusion-invariant features.
… method achieves a state-of-the-art performance among weakly supervised one-step person search approaches …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
