Reidentify people in new scenes better by accounting for camera styles with CA-UReID
Reidentify people in new scenes better by accounting for camera styles with CA-UReID
Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification
arXiv paper abstract https://arxiv.org/abs/2112.10089v1
arXiv PDF paper https://arxiv.org/pdf/2112.10089v1.pdf
Unsupervised person re-identification (ReID) is a challenging task without data annotation to guide discriminative learning.
Existing methods attempt to solve this problem by clustering extracted embeddings to generate pseudo labels.
However, most methods ignore the intra-class gap caused by camera style variance
... propose a camera-aware style separation and contrastive learning method (CA-UReID), which directly separates camera styles in the feature space
It can explicitly divide the learnable feature into camera-specific and camera-agnostic parts, reducing the influence of different cameras.
... demonstrate the superiority of our method over the state-of-the-art methods on the unsupervised person ReID task.
Please like and share this post if you enjoyed it using the buttons at the bottom!
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
Comments