相似性最小-最大：零样本昼夜域自适应
Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation
AI总结：
针对零样本昼夜域自适应无需夜间数据的需求，提出相似性最小-最大范式，联合优化图像级变暗增广与模型级特征对齐，显著提升模型泛化性，在多类夜间视觉任务上验证了有效性。
摘要：
低光照条件不仅会影响人类的视觉体验，还会降低模型在下游视觉任务上的性能。尽管现有工作在昼夜域自适应方面取得了显著进展，但它们严重依赖从特定任务的夜间数据集所获得的领域知识。本文针对一个更具普适性的复杂场景展开研究，即零样本昼夜域自适应，该场景消除了对任何夜间数据的依赖。与以往要么强调图像级转换要么强调模型级自适应的零样本自适应方法不同，我们提出了一种相似性最小-最大范式，在统一框架下考量这两者。在图像层面，我们将图像变暗，使特征相似度最小化，从而扩大域间隙。然后在模型层面，我们最大化变暗图像与其正常光照对应图像之间的特征相似度，以实现更好的模型自适应。据我们所知，这项工作是首次联合优化这两个方面的开创性努力，显著提升了模型的泛化能力。大量实验证明了我们的方法在多种夜间视觉任务上的有效性和广泛适用性，包括分类、语义分割、视觉位置识别和视频动作识别。代码和预训练模型可在https://red-fairy.github.io/ZeroShotDayNightDA-Webpage/获取。
英文摘要：
Low-light conditions not only hamper human visual experience but also degrade the model's performance on downstream vision tasks. While existing works make remarkable progress on day-night domain adaptation, they rely heavily on domain knowledge derived from the task-specific nighttime dataset. This paper challenges a more complicated scenario with border applicability, i.e., zero-shot day-night domain adaptation, which eliminates reliance on any nighttime data. Unlike prior zero-shot adaptation approaches emphasizing either image-level translation or model-level adaptation, we propose a similarity min-max paradigm that considers them under a unified framework. On the image level, we darken images towards minimum feature similarity to enlarge the domain gap. Then on the model level, we maximize the feature similarity between the darkened images and their normal-light counterparts for better model adaptation. To the best of our knowledge, this work represents the pioneering effort in jointly optimizing both aspects, resulting in a significant improvement of model generalizability. Extensive experiments demonstrate our method's effectiveness and broad applicability on various nighttime vision tasks, including classification, semantic segmentation, visual place recognition, and video action recognition. Code and pre-trained models are available at https://red-fairy.github.io/ZeroShotDayNightDA-Webpage/.
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。
