AI 中文总结
针对开放词汇目标检测测试时适应的缺陷，提出PISA框架，利用CIFE、FAM、BAA模块，无需源域数据，在损坏基准上实现最优性能，提升检测精度。
AI 中文摘要
开放词汇目标检测测试时适应（OVOD-TTA）旨在解决预训练基础模型在遇到图像域偏移时出现的性能下降问题。现有的无数据源OVOD-TTA方法要么依赖精细的测试时信息进行重新评分，要么依赖伪标签进行自训练，当初始预测效果较差时会导致显著的精度下降。同时，大多数传统源域估计方法会恢复适用于分类任务的抽象、稀疏表示，但无法捕获检测所需的密集、具体特征。为解决这些问题，我们提出PISA，一种可无缝集成到开放词汇视觉骨干网络的新型无数据源OVOD-TTA方法。该方法的核心组件包括：不变性特征提取器（CIFE）、特征对齐模块（FAM）和多尺度对齐框架（BAA）。为捕获适用于检测的特征，我们开发CIFE以利用CLIP视觉特征在损坏图像上的不变性，确保对各种损坏的鲁棒性。我们进一步开发FAM和BAA，用于预训练和适应，将损坏不变性特征转换为接近原始源域特征的伪个体源域特征。通过这种方式，使用密集且具体的伪个体源域特征进行监督，而非不可靠的伪标签信号。在损坏的VOC-C、COCO-C和LVIS-C基准上，针对三个基础模型开展的实验表明，PISA显著提升了原始模型的定位精度和类别识别准确率。值得注意的是，PISA无需访问源域数据即可实现最先进的性能，在COCO-C上的AP@50%指标较现有方法超出3.92%。
英文摘要
Open-vocabulary object detection test-time adaptation (OVOD-TTA) aims to address the performance degradation that pre-trained base models suffer when encountering image-domain shifts. Existing source-free OVOD-TTA methods rely either on refined test-time information for re-scoring or on pseudo-labels for self-training, leading to significant accuracy degradation when initial predictions are poor. Meanwhile, most conventional source-domain estimation methods recover abstract, sparse representations suitable for the classification task, but fail to capture the dense, concrete features required for detection. To address these issues, we propose PISA, a novel source-free OVOD-TTA method that can be seamlessly integrated into open-vocabulary visual backbones. The core components of our method are the Corruption-Invariant Feature Extractor (CIFE), the Feature Alignment Module (FAM), and a multi-scale alignment framework (BAA). To capture detection-suitable features, we develop CIFE to exploit the invariance of CLIP's visual features across corrupted images, ensuring robustness against various corruptions. We further develop FAM and BAA for the pre-training and adaptation to transform the corruption-invariant features into pseudo-individual source-domain features that are close to the original source-domain features. In this way, dense and concrete pseudo-individual source-domain features are used for supervision instead of unreliable pseudo-label signals. Experiments on the corrupted VOC-C, COCO-C, and LVIS-C benchmarks across three base models demonstrate that PISA substantially improves both the localization precision and the category recognition accuracy of the original models. Notably, PISA achieves state-of-the-art performance without requiring access to source-domain data, surpassing existing methods by 3.92% in AP@50% on COCO-C.
