DiCLIP uses diffusion-based visual correlation enhancement and text semantic augmentation to improve CLIP-generated class activation maps for weakly supervised semantic segmentation, outperforming prior methods on PASCAL VOC and MS COCO.
Tackling ambi- guity from perspective of uncertainty inference and affinity diversifi- cation for weakly supervised semantic segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation
DiCLIP uses diffusion-based visual correlation enhancement and text semantic augmentation to improve CLIP-generated class activation maps for weakly supervised semantic segmentation, outperforming prior methods on PASCAL VOC and MS COCO.