Segment objects with only image labels using negative region of interest with FBR
Segment objects with only image labels using negative region of interest with FBR
Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
arXiv paper abstract https://arxiv.org/abs/2406.15755
arXiv PDF paper https://arxiv.org/pdf/2406.15755
Generating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information.
… proposes a simple fine-grained background representation (FBR) method to discover and represent diverse BG semantics and address the co-occurring problems.
… develop a … negative region of interest (NROI), to capture the fine-grained BG semantic information and conduct the pixel-to-NROI contrast to distinguish the confusing BG pixels.
… present an active sampling strategy to mine the FG negatives on-the-fly, enabling … pixel-to-pixel intra-foreground contrastive learning to activate the entire object region.
… proposed method can be seamlessly plugged into various models, yielding new state-of-the-art results under various WSSS settings across benchmarks.
Leveraging solely image-level (I) labels as supervision, … method achieves 73.2 mIoU and 45.6 mIoU segmentation results on Pascal Voc and MS COCO test sets, respectively …
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
