超越启发式提示词：面向零样本图像识别的概念引导贝叶斯框架
Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition
把类别概念当作潜变量、用贝叶斯边缘化替代启发式提示词集成，并配一个无需训练的自适应软裁剪似然来压制离群概念——这套思路可直接迁移到 CLIP 类模型的零样本/少样本识别与开放词表分类中，替代手工 prompt 模板搜索。
原文依据 treating concepts as latent variables, we rethink zero-shot image classification from a Bayesian perspective
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）已显著推进了零样本图像识别。然而，其性能仍受制于次优的提示词工程以及对目标类别适应性差的问题。尽管近期方法试图通过多样化的类别描述来改进提示词，但它们往往依赖启发式设计、缺乏通用性，且易受离群提示词影响。本文通过引入类别特定概念来增强提示词。我们将概念视为潜变量，从贝叶斯视角重新审视零样本图像分类，把预测表述为在概念空间上的边缘化，其中每个概念由先验与以测试图像为条件的似然加权。这一表述凸显了结构良好的概念提议分布与概念先验精化的双重重要性。为构建表达力强且高效的提议分布，我们引入由大语言模型驱动的多阶段概念合成流程，以生成具有判别性与组合性的概念，随后用行列式点过程保证多样性。为缓解离群概念的影响，我们提出一种无需训练的自适应软裁剪似然，在单次前向传播中削弱其影响。我们进一步给出该框架的鲁棒性保证，并推导多类超额风险界。大量实验表明，本方法持续优于最优方法，验证了其在零样本图像分类中的有效性。
英文原文摘要 1546 字符
Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering and poor adaptability to target classes. While recent methods attempt to improve prompts through diverse class descriptions, they often rely on heuristic designs, lack versatility, and are vulnerable to outlier prompts. This paper enhances prompt by incorporating class-specific concepts. By treating concepts as latent variables, we rethink zero-shot image classification from a Bayesian perspective, casting prediction as marginalization over the concept space, where each concept is weighted by a prior and a test-image conditioned likelihood. This formulation underscores the importance of both a well-structured concept proposal distribution and the refinement of concept priors. To construct an expressive and efficient proposal distribution, we introduce a multi-stage concept synthesis pipeline driven by LLMs to generate discriminative and compositional concepts, followed by a Determinantal Point Process to enforce diversity. To mitigate the influence of outlier concepts, we propose a training-free, adaptive soft-trim likelihood, which attenuates their impact in a single forward pass. We further provide robustness guarantees and derive multi-class excess risk bounds for our framework. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches, validating its effectiveness in zero-shot image classification.