兼顾双向：面向开放词表伪装目标分割的双向语义对齐
Seeing Both Sides: Towards Bidirectional Semantic Alignment for Open-Vocabulary Camouflaged Object Segmentation
提出双向跨注意力实现视觉-文本特征互校准，并将精炼后的文本嵌入转为自适应提示词驱动 SAM 生成掩码，可直接用于开放词表分割与跨模态提示学习。
原文依据 we propose BaCLIP, a novel bidirectional semantic alignment framework for OVCOS
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论开放词表伪装目标分割（OVCOS）旨在文本引导下精确分割未见类别的伪装目标。然而，现有方法通常采用单向交互策略，由文本提示词引导视觉特征的匹配。这种设计忽略了视觉与语言模态之间的双向交互，使模型易受图像级文本语义与像素级分割线索之间语义鸿沟的影响，进而在复杂伪装场景中导致严重的语义混淆。为解决该挑战，我们提出 BaCLIP，一种面向 OVCOS 的新型双向语义对齐框架。其核心是互精炼与增强模块（MREM），该模块在视觉与文本特征之间建立双向交叉注意力，实现相互语义校准以消除歧义并增强跨模态对齐。此外，我们引入自适应提示词，将精炼后的文本嵌入转化为面向 Segment Anything Model（SAM）的语义感知提示词，实现直接的文本引导并提升掩码精度。在 OVCamo 基准上的实验结果表明，BaCLIP 以紧凑架构持续取得最优性能，有效缓解语义混淆并推进跨模态伪装感知的理解。代码已发布于 https://github.com/okmaybach/BaCLIP-CVPR2026。
英文原文摘要 1484 字符
Open-Vocabulary Camouflaged Object Segmentation (OVCOS) aims to segment camouflaged objects from unseen categories under textual guidance precisely. However, existing methods often employ a unidirectional interaction strategy, where textual prompts guide the matching of visual features. Such a design neglects the bidirectional interaction between visual and language modalities, making the model vulnerable to the semantic gap between image-level textual semantics and pixel-level segmentation cues, which in turn leads to severe semantic confusion in complex camouflaged scenarios. To address this challenge, we propose BaCLIP, a novel bidirectional semantic alignment framework for OVCOS. At its core lies the Mutual Refinement and Enhancement Module (MREM), which establishes bidirectional cross-attention between visual and textual features, enabling mutual semantic calibration to resolve ambiguity and strengthen cross-modal alignment. Moreover, we introduce an Adaptive Prompt that transforms refined textual embeddings into semantic-aware prompts for Segment Anything Model (SAM), enabling direct textual guidance and improving mask precision. Experimental results on the OVCamo benchmark demonstrate that BaCLIP consistently achieves state-of-the-art performance with a compact architecture, effectively mitigating semantic confusion and advancing the understanding of cross-modal camouflage perception. Our code is released at https://github.com/okmaybach/BaCLIP-CVPR2026.