View PDF (https://arxiv.org/pdf/2606.30795)HTML (experimental) (https://arxiv.org/html/2606.30795v1) Abstract:Source-free domain adaptive object detection adapts a source-trained detector to an unlabeled target domain, typically through teacher-student self-training with pseudo-labels. We revisit this setting when a small, uniformly sampled subset of target images is labeled. We introduce Random-Target Supervised Mixing (RTSM), a simple anchor that incorporates these annotations through a supervised detection loss while leaving the original unlabeled adaptation branch unchanged. Across evaluations spanning four SFDA-OD methods, two object detectors, multiple adaptation tasks, and target-label budgets from 1% to 10%, RTSM consistently improves pure SFDA by 1.7 to 18.3 AP50. We then examine whether the same annotations can provide further gains by steering unlabeled self-training. To this end, we evaluate ten sparse-label feedback plugins covering pseudo-label selection, object completion, and optimization control, which yield limited and method-dependent gains over RTSM. These results reveal a bitter lesson for sparse-label SFDA-OD: simple supervision is hard to beat. RTSM therefore provides a simple yet effective anchor for sparse-label SFDA-OD. Subjects:Computer Vision and Pattern Recognition (cs.CV) Cite as:arXiv:2606.30795 (https://arxiv.org/abs/2606.30795) [cs.CV] (or arXiv:2606.30795v1 (https://arxiv.org/abs/2606.30795v1) [cs.CV] for this version) https://doi.org/10.48550/arXiv.2606.30795 arXiv-issued DOI via DataCite (pending registration) Submission history From: Lijun Zhang [view email (https://arxiv.org/show-email/3d24ec30/2606.30795)] • *[v1]** Mon, 29 Jun 2026 18:21:09 UTC (291 KB)