SOURCE-LINKED INTELLIGENCE

ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object Segmentation

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Open-vocabulary camouflaged object segmentation (OVCOS) aims to segment unseen camouflaged objects under text guidance. We observe that SAM3 still suffers from a pronounced semantic gap between global textual semantics and fine-grained pixel-level visual cues in OVCOS. Meanwhile, fully fine-tuning the text encoder introduces heavy parameter overhead and risks overfitting to training categories, which compromises open-vocabulary representation flexibility. To address these issues, we propose ViCo-SAM3, a Vision-Conditioned alignment framework designed for OVCOS. Specifically, we introduce visio

Read original source ↗ Open in workspace

recordType

paper

region

Global