Low-Confidence Pseudo-Label Decoupling Exploration for Source Free Object Detection

Source-free object detection (SFOD) transfers a source-trained model to a target domain using only unlabeled data. Most SFOD methods adopt a mean-teacher framework, filtering pseudo labels by teacher confidence and alternately updating student and teacher models. However, this may discard high-quality low-confidence pseudo labels, as confidence alone does not reflect label quality. To better exploit these labels, we propose Decoupled Pseudo-label Learning (DPL), which disentangles classification and localization to identify high-quality pseudo labels. DPL comprises a double confirmation class mechanism and jitter-based localization evaluation to handle low-confidence labels in terms of category and localization. After obtaining high-quality pseudo labels, mixed contrastive learning further enhances target-domain representation. Extensive experiments demonstrate that DPL achieves state-of-the-art performance.