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

2026-09-14

AI Summary

为解决OVCOS中视觉与文本语义鸿沟问题，提出ViCo-SAM3框架，通过视觉条件模块动态调整文本嵌入，增强跨模态交互。

Abstract

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 vision-conditioned (ViCo) module, which dynamically modulates text embeddings with global visual context, enabling textual representations to adapt to the current image content and thereby effectively bridging the semantic gap between vision and text. Building on this, we further design a vision-conditioned cross-modal binding (ViCoBind) module to enhance cross-modal interaction and semantic alignment between visual and textual representations. Without bells and whistles, ViCo-SAM3 achieves state-of-the-art performance on the OVCamo benchmark and demonstrates strong generalization.

Problem

• Open-vocabulary camouflaged object segmentation
• Semantic gap
• Text guidance

Innovation

• Vision-Conditioned Alignment
• Open-Vocabulary Camouflaged Object Segmentation
• Cross-Modal Binding
• Semantic Gap