对齐你的提示：基于分布对齐的测试时提示方法实现零样本泛化
Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization
AI总结：
本文提出通过测试时提示调优对齐OOD测试样本与源数据的特征分布，以缓解分布偏移，在领域泛化和跨数据集泛化任务上超越现有提示学习方法。
摘要：
视觉-语言模型（如CLIP）展现出的良好零样本泛化能力，使其通过提示学习被广泛应用于众多下游任务。此前的工作表明，利用熵最小化的测试时提示调优可以针对未见领域调整文本提示。虽然该方法有效，但忽略了导致未见领域性能下降的关键原因——分布偏移。在本工作中，我们通过使用提示调优将分布外（OOD）测试样本的统计特征与源数据对齐，明确处理这一问题。我们使用单个测试样本，在测试时通过最小化特征分布偏移来适配多模态提示，从而弥合测试领域的差距。在领域泛化基准上的评估表明，我们的方法在零样本top-1准确率上超越了现有提示学习技术，比基线MaPLe提高了3.08%。在跨数据集泛化实验中，涉及10个数据集中的未见类别，与现有最先进方法相比，我们的方法在所有数据集上均取得了一致的提升。我们的源代码和模型可在https://jameelhassan.github.io/promptalign获取。
英文摘要：
The promising zero-shot generalization of vision-language models such as CLIP has led to their adoption using prompt learning for numerous downstream tasks. Previous works have shown test-time prompt tuning using entropy minimization to adapt text prompts for unseen domains. While effective, this overlooks the key cause for performance degradation to unseen domains -- distribution shift. In this work, we explicitly handle this problem by aligning the out-of-distribution (OOD) test sample statistics to those of the source data using prompt tuning. We use a single test sample to adapt multi-modal prompts at test time by minimizing the feature distribution shift to bridge the gap in the test domain. Evaluating against the domain generalization benchmark, our method improves zero-shot top- 1 accuracy beyond existing prompt-learning techniques, with a 3.08% improvement over the baseline MaPLe. In cross-dataset generalization with unseen categories across 10 datasets, our method improves consistently across all datasets compared to the existing state-of-the-art. Our source code and models are available at https://jameelhassan.github.io/promptalign.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
