Work

SPL: stable pseudo-label learning for domain adaptive object detection

Year: 2026
Type: article
Abstract: Domain-adaptive object detection uses labelled source images and unlabelled target images to address distribution shift. We introduce stable pseudo-label learning (SPL), an incremental extension of the JMT-YOLO Mean Teacher framework that couples adaptive filtering with dynamic assignment. Distribution-aware adaptive thresholding (DAAT) applies Otsu’s between-group variance criterion to a 100-bin histogram of teacher confidence scores and smooths the resulting threshold over iterations. Dynamic pseudo-label assignment (DPLA) restricts candidates by pseudo-box centres, combines classification, overlap and centre-distance costs, and uses IoU-based dynamic positive counts with minimum-cost conflict resolution. SPL obtained 48.6% and 58.4% [email protected] on Pascal VOC \(\rightarrow\) Clipart1k and Cityscapes \(\rightarrow\) Foggy Cityscapes, respectively, and 62.8% Car [email protected] on KITTI \(\rightarrow\) Cityscapes. The corresponding gains over JMT-YOLO were 1.7, 1.1 and 1.8 percentage points. Component ablations support an incremental detection benefit in the evaluated framework. The evaluation covers style, weather and camera shifts within JMT-YOLO, with target-validation-informed model selection.
Language: English
Open Access status: gold
Estimated APC paid: $2,690
OpenAlex ID: W7233273250
FWCI:
Cites: 27
Cited by:
Related to: 10