Domain adaptation helps generalizing object detection models to target domain data with distribution shift. It is often achieved by adapting with access to the whole target domain data. In a more realistic scenario, target distribution is often unpredictable until inference stage. This motivates us to explore adapting an object detection model at test-time, a.k.a. test-time adaptation (TTA). In this work, we approach test-time adaptive object detection (TTAOD) from two perspective. First, we adopt a self-training paradigm to generate pseudo labeled objects with an exponential moving average model. The pseudo labels are further used to supervise adapting source domain model. As self-training is prone to incorrect pseudo labels, we further incorporate aligning feature distributions at two output levels as regularizations to self-training. To validate the performance on TTAOD, we create benchmarks based on three standard object detection datasets and adapt generic TTA methods to object detection task. Extensive evaluations suggest our proposed method sets the state-of-the-art on test-time adaptive object detection task.

翻译：领域自适应有助于将目标检测模型泛化至存在分布偏移的目标域数据，通常需访问全部目标域数据实现自适应。在更实际场景中，目标分布往往在推理阶段前不可预测，这促使我们探索测试时自适应（TTA）的目标检测模型。本文从两个角度探讨测试时自适应目标检测（TTAOD）：首先，采用自训练范式，通过指数移动平均模型生成伪标签对象，并利用伪标签监督源域模型的自适应过程；其次，针对自训练易受错误伪标签影响的问题，进一步在两个输出层级引入特征分布对齐作为正则化约束。为验证TTAOD性能，我们基于三个标准目标检测数据集构建基准，并将通用TTA方法适配至目标检测任务。大量评估表明，所提方法在测试时自适应目标检测任务上达到最优性能。