Improve vision tasks with people using cells of various shapes with TCFormer
Improve vision tasks with people using cells of various shapes with TCFormer
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
arXiv paper abstract https://arxiv.org/abs/2204.08680v2
arXiv PDF paper https://arxiv.org/pdf/2204.08680v2.pdf
Vision transformers have achieved great successes in many computer vision tasks.
Most methods generate vision tokens by splitting an image into a regular and fixed grid and treating each cell as a token.
However, not all regions are equally important in human-centric vision tasks, e.g., the human body needs a fine representation with many tokens
... propose .. Vision Transformer, called Token Clustering Transformer (TCFormer), which merges tokens by ... clustering, where the tokens can be merged from different locations with flexible shapes and sizes.
.. tokens .. can not only focus on important areas but also adjust the token shapes to fit the semantic concept and adopt a fine resolution for regions containing critical details
... TCFormer ... outperforms its counterparts on ... challenging human-centric tasks and datasets, including whole-body pose estimation ... and 3D human mesh reconstruction ...
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