BiomedCCPL：面向生物医学视觉语言模型的因果条件提示词学习
BiomedCCPL: Causal Conditional Prompt Learning for Biomedical Vision-Language Models
用因果前门调整约束图像条件提示词的生成，使提示词只依赖跨类共享的诊断性视觉特征，这一思路可直接迁移到任何 VLM 的 base-to-novel 泛化场景，用来抑制已见类中的虚假线索。
原文依据 SCD leverages multiple synergistic learning objectives to perform front-door adjustment
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（VLM）在训练样本有限的情况下展现出适配下游生物医学任务的强大潜力。然而，它们在同一数据集内对未见类别的泛化能力仍然有限，因为图文对齐语义往往依赖已见类别中存在、却无法迁移的虚假线索。为解决这一问题，我们提出 BiomedCCPL（因果条件提示词学习），该框架使用 VGAP（带自适应原型的视觉定位器）从多尺度自适应原型生成图像条件提示词，并采用 SCD（协同因果解耦）对图像条件提示词的生成进行正则化。在对未见类别泛化的因果分析所得洞见的指导下，SCD 利用多个协同学习目标执行前门调整，确保动态生成的图像条件提示词聚焦于已见与未见类别共享的底层诊断图像特征。在涵盖 9 种模态的 11 个数据集上的实验表明，BiomedCCPL 有效提升了模型的数据效率与泛化能力。特别是在基类到新类任务上，BiomedCCPL 取得了 79.98% 的平均 HM，较此前的最优方法高出 6.45%。代码已发布于 https://github.com/burgers0708/BiomedCCPL。
英文原文摘要 1345 字符
Vision-language models (VLMs) have demonstrated strong potential for adapting to downstream biomedical tasks with limited training samples. However, their generalization to unseen classes within the same dataset remains limited, as the image-text alignment semantics often rely on spurious cues present in seen classes that do not transfer. To tackle this, we propose BiomedCCPL (Causal Conditional Prompt Learning), a framework that uses VGAP (Visual Grounder with Adaptive Prototype) to generate image-conditional prompts from multi-scale adaptive prototypes and employs SCD (Synergistic Causal Disentanglement) to regularize the generation of image-conditional prompts. Guided by insights from a causal analysis of generalization to unseen classes, SCD leverages multiple synergistic learning objectives to perform front-door adjustment, ensuring that the dynamically generated image-conditional prompts focus on underlying diagnostic image features shared across seen and unseen classes. Experiments on 11 datasets across 9 modalities demonstrate that BiomedCCPL effectively enhances the model's data efficiency and generalization ability. In particular, on the Base-to-Novel task, BiomedCCPL achieves an average HM of 79.98%, surpassing the previous state-of-the-art by 6.45%. Code is available at https://github.com/burgers0708/BiomedCCPL.