AI RESEARCH
CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection
arXiv CS.CV
•
ArXi:2604.16854v1 Announce Type: new Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors have become the mainstream approach and achieve state-of-the-art (SoTA) accuracy, yet their substantial computational overhead severely limits practical deployment. To address this, we propose a hierarchical Confidence-Aware Token Pruning framework (CATP) tailored for.