Train object segmentation with only boxes by using transformers as mask auto-labeler with MAL
Train object segmentation with only boxes by using transformers as mask auto-labeler with MAL
Vision Transformers Are Good Mask Auto-Labelers
arXiv paper abstract https://arxiv.org/abs/2301.03992
arXiv PDF paper https://arxiv.org/pdf/2301.03992.pdf
… propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask auto-labeling framework for instance segmentation using only box annotations.
MAL takes box-cropped images as inputs and conditionally generates their mask pseudo-labels … show that Vision Transformers are good mask auto-labelers.
… method significantly reduces the gap between auto-labeling and human annotation regarding mask quality.
Instance segmentation models trained using the MAL-generated masks can nearly match the performance of their fully-supervised counterparts, retaining up to 97.4% performance of fully supervised models.
The best model achieves 44.1% mAP on COCO instance segmentation (test-dev 2017), outperforming state-of-the-art box-supervised methods by significant margins.
Qualitative results indicate that masks produced by MAL are, in some cases, even better than human annotations.
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
