Refined Pseudo labeling for Source-free Domain Adaptive Object Detection
This work addresses domain shift in object detection for real-world applications where source data is unavailable, representing an incremental improvement over existing methods.
The paper tackled the problem of biased pseudo labels in source-free domain adaptive object detection by proposing a refined pseudo labeling framework with category-aware adaptive thresholds and localization-aware assignment, achieving state-of-the-art performance on four adaptation tasks.
Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real-world scenarios. Thus, source-free DAOD is proposed to adapt the source-trained detectors to target domains with only unlabeled target data. Existing source-free DAOD methods typically utilize pseudo labeling, where the performance heavily relies on the selection of confidence threshold. However, most prior works adopt a single fixed threshold for all classes to generate pseudo labels, which ignore the imbalanced class distribution, resulting in biased pseudo labels. In this work, we propose a refined pseudo labeling framework for source-free DAOD. First, to generate unbiased pseudo labels, we present a category-aware adaptive threshold estimation module, which adaptively provides the appropriate threshold for each category. Second, to alleviate incorrect box regression, a localization-aware pseudo label assignment strategy is introduced to divide labels into certain and uncertain ones and optimize them separately. Finally, extensive experiments on four adaptation tasks demonstrate the effectiveness of our method.