Weakly supervised segmentation using extracted semantic features from CLIP with WeCLIP
Weakly supervised segmentation using extracted semantic features from CLIP with WeCLIP
Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2406.11189
arXiv PDF paper https://arxiv.org/pdf/2406.11189
… propose WeCLIP, a CLIP-based single-stage pipeline, for weakly supervised semantic segmentation.
… the frozen CLIP model is applied as the backbone for semantic feature extraction, and a new decoder is designed to interpret extracted semantic features for final prediction.
… utilize the above frozen backbone to generate pseudo labels for training the decoder. Such labels cannot be optimized during training.
… propose a refinement module (RFM) to rectify them dynamically … architecture enforces the proposed decoder and RFM to benefit from each other to boost the final performance.
… approach significantly outperforms other approaches with less training cost.
Additionally, … WeCLIP also obtains promising results for fully supervised settings …
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
