Vision-language models (VLMs) such as CLIP and Grounding DINO have achieved remarkable success in object recognition and detection. However, their performance often degrades under real-world distribution shifts. Test-time adaptation (TTA) aims to mitigate this issue by adapting models during inference. Existing methods either rely on computationally expensive backpropagation, which hinders real-time deployment, or focus solely on likelihood adaptation, which overlooks the critical role of the prior. Our prior work, Bayesian Class Adaptation (BCA), addressed these shortcomings for object recognition by introducing a training-free framework that incorporates adaptive priors. Building upon this foundation, we now present Bayesian Class Adaptation plus (BCA+), a unified, training-free framework for TTA for both object recognition and detection. BCA+ introduces a dynamic cache that adaptively stores and updates class embeddings, spatial scales (for detection), and, crucially, adaptive class priors derived from historical predictions. We formulate adaptation as a Bayesian inference problem, where final predictions are generated by fusing the initial VLM output with a cache-based prediction. This cache-based prediction combines a dynamically updated likelihood (measuring feature and scale similarity) and a prior (reflecting the evolving class distribution). This dual-adaptation mechanism, coupled with uncertainty-guided fusion, enables BCA+ to correct both the model's semantic understanding and its contextual confidence. As a training-free method requiring no backpropagation, BCA+ is highly efficient. Extensive experiments demonstrate that BCA+ achieves state-of-the-art performance on both recognition and detection benchmarks.

翻译：诸如CLIP和Grounding DINO等视觉语言模型（VLMs）在目标识别与检测任务中取得了显著成功。然而，在现实世界的分布偏移下，其性能常常出现退化。测试时适应（TTA）旨在通过在推理阶段对模型进行适应来缓解这一问题。现有方法要么依赖于计算成本高昂的反向传播，这阻碍了实时部署；要么仅关注似然适应，而忽视了先验分布的关键作用。我们先前的工作——贝叶斯类别适应（BCA）——通过引入一个包含自适应先验的无训练框架，针对目标识别任务解决了这些缺陷。基于此基础，我们现在提出贝叶斯类别适应增强版（BCA+），一个用于目标识别与检测的统一、无训练的TTA框架。BCA+引入了一个动态缓存，该缓存自适应地存储和更新类别嵌入、空间尺度（用于检测），以及至关重要的、源自历史预测的自适应类别先验。我们将适应过程表述为一个贝叶斯推断问题，其中最终预测通过融合初始VLM输出与基于缓存的预测来生成。该基于缓存的预测结合了动态更新的似然（度量特征与尺度相似性）和一个先验（反映演变的类别分布）。这种双重适应机制，结合不确定性引导的融合，使得BCA+能够同时修正模型的语义理解及其上下文置信度。作为一种无需反向传播的无训练方法，BCA+具有很高的效率。大量实验表明，BCA+在识别与检测基准测试中均达到了最先进的性能。