Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.
In: Proceedings of the IEEE conference on computer vision and pattern recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ModuSeg enables training-free weakly supervised semantic segmentation by explicitly separating geometric object discovery from non-parametric semantic feature retrieval using existing mask proposers and foundation model feature banks.
citing papers explorer
-
How to Evaluate and Refine your CAM
Introduces synthetic ground-truth dataset for CAM evaluation, proposes ARCC composite metric, and RefineCAM method that aggregates layers for higher-resolution maps outperforming baselines.
-
ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation
ModuSeg enables training-free weakly supervised semantic segmentation by explicitly separating geometric object discovery from non-parametric semantic feature retrieval using existing mask proposers and foundation model feature banks.