2 papers
cs.CV2025
Lightweight Transformer Framework for Weakly Supervised Semantic Segmentation
Ali Torabi, Sanjog Gaihre, Yaqoob Majeed
Weakly supervised semantic segmentation (WSSS) must learn dense masks from noisy, under-specified cues. We revisit the SegFormer decoder and show that three small, synergistic chan…
cs.CV2025
Localized Region Guidance for Class Activation Mapping in WSSS
Ali Torabi, Sanjog Gaihre, MD Mahbubur Rahman +1
Weakly Supervised Semantic Segmentation (WSSS) addresses the challenge of training segmentation models using only image-level annotations. Existing WSSS methods struggle with preci…