Reidentify people in new scenes better by using multiple networks
Reidentify people in new scenes better by using multiple networks
Learning to Disentangle Scenes for Person Re-identification
arXiv paper abstract https://arxiv.org/abs/2111.05476v1
arXiv PDF paper https://arxiv.org/pdf/2111.05476v1.pdf
There are many challenging problems in the person re-identification (ReID) task, such as the occlusion and scale variation.
... usually tried to solve them by employing ... one-branch network needs to be robust to various challenging problems, which makes this network overburdened.
... proposes ... employ several self-supervision operations to simulate different challenging problems and handle each challenging problem using different networks.
... use the random erasing operation and propose a novel random scaling operation to generate new images with controllable characteristics.
A general multi-branch network ... introduced to handle different scenes ... In this way ... are effectively disentangled ...
... method achieves state-of-the-art performances on three ReID benchmarks and two occluded ReID benchmarks. ...
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