基于细粒度对象绑定与自适应混合提示词的训练无关开放词表伪装目标分割
Training-Free Open-Vocabulary Camouflaged Object Segmentation via Fine-Grained Object Binding and Adaptive Hybrid Prompt
提出训练无关的开放词表伪装目标分割框架，利用MLLM生成细粒度文本描述，并通过语义探针和语义一致性排序实现视觉块与类别的精确绑定，结合熵引导的文本嵌入调整和自适应混合提示词生成，为SAM提供更准确的提示，可复用于其他开放词表分割任务。
原文依据 we propose a fine-grained object binding and adaptive hybrid prompt framework for training-free 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视觉语言模型（如CLIP）促进了开放词表伪装目标分割（OVCOS）的发展，但现有方法仍依赖掩码标注进行全监督训练。相比之下，训练无关范式能够快速处理未见数据，是一种极具前景的解决方案。然而，在伪装场景下，现有训练无关方法使用稀疏文本提示词并忽略视觉块之间的类别相似性，导致对象绑定能力不足。为缓解这些问题，我们提出了一种用于训练无关OVCOS的细粒度对象绑定与自适应混合提示词框架。该框架首先利用多模态大语言模型（MLLMs）显式建模伪装对象和背景的细粒度文本描述。在此基础上，我们构建了一个语义探针来解耦对象和背景特征，并通过语义一致性排序显式建模视觉块之间的类别相似性，从而实现准确的对象绑定。随后，我们提出了一种熵引导的文本嵌入调整策略来调整文本嵌入，旨在进一步增强细粒度对象绑定。最后，我们利用自适应混合提示词生成策略生成混合提示词，辅助SAM准确分割伪装对象。在OVCamo基准上的实验结果表明，我们的方法取得了优异性能，显著超越了先进的训练无关方法ResCLIP。
英文原文摘要 1531 字符
Vision-Language models (e.g., CLIP) facilitate the development of open-vocabulary camouflaged object segmentation (OVCOS), but existing methods still rely on mask annotations for fully-supervised training. In contrast, the training-free paradigm can rapidly process unseen data, representing a highly promising solution. However, in camouflage scenarios, existing training-free methods utilize sparse textual prompts and ignore the category similarity between visual patches, leading to inadequate object binding capability. To alleviate these issues, we propose a fine-grained object binding and adaptive hybrid prompt framework for training-free OVCOS. The framework first employs multimodal large language models (MLLMs) to explicitly model fine-grained textual descriptions of camouflaged objects and background. Building on this, we construct a semantic probe to decouple object and background features and explicitly model category similarity between visual patches via semantic consistency ranking, thereby achieving accurate object binding. Subsequently, we propose an entropy-guided text embedding adjustment strategy to adjust textual embeddings, aiming to further enhance fine-grained object binding. Finally, we utilize an adaptive hybrid prompt generation strategy to generate hybrid prompts, assisting SAM in accurately segmenting camouflaged objects. Experimental results on the OVCamo benchmark demonstrate that our method achieves excellent performance, significantly surpassing the advanced training-free ResCLIP.