A dual-hypothesis segmentation architecture with prosecution/defense streams and an RL judge model achieves superior performance in localizing image manipulations by explicitly contrasting evidence.
Boundary-guided camouflaged object detection
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
BASFNet fuses boundary-aware frequency-domain edge exploration with spatial core segmentation and interaction modules to outperform prior methods on camouflaged object detection benchmarks.
EviRCOD integrates reference-guided deformable encoding, uncertainty-aware evidential decoding, and boundary refinement to achieve state-of-the-art performance on referring camouflaged object detection benchmarks with calibrated uncertainty.
GLASSNet outperforms prior methods on salient object detection benchmarks by freezing SAMv2, adding a spatially aware adapter, and fusing outputs from global and local decoders.
citing papers explorer
-
The Courtroom Trial of Pixels: Robust Image Manipulation Localization via Adversarial Evidence and Reinforcement Learning Judgment
A dual-hypothesis segmentation architecture with prosecution/defense streams and an RL judge model achieves superior performance in localizing image manipulations by explicitly contrasting evidence.
-
Exploring Boundary-Aware Spatial-Frequency Fusion for Camouflaged Object Detection
BASFNet fuses boundary-aware frequency-domain edge exploration with spatial core segmentation and interaction modules to outperform prior methods on camouflaged object detection benchmarks.
-
EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
EviRCOD integrates reference-guided deformable encoding, uncertainty-aware evidential decoding, and boundary refinement to achieve state-of-the-art performance on referring camouflaged object detection benchmarks with calibrated uncertainty.
-
Global-Local Feature Decoding with Adapter-Guided SAMv2 for Salient Object Detection
GLASSNet outperforms prior methods on salient object detection benchmarks by freezing SAMv2, adding a spatially aware adapter, and fusing outputs from global and local decoders.