Source-free object detection (SFOD) faces persistent challenges due to class imbalance–driven context bias and instability in teacher–student training under noisy pseudo-labels. Existing techniques tend to ignore the context bias and class imbalance shift, especially in medical data. To tackle this, we propose Grounded Teacher (GT), a bias-aware source-free framework that grounds the teacher model through relational and semantic regularization.. To explicitly model directional confusions between classes, GT introduces a Relational Context Module (RCM), which maintains an exponential moving average (EMA) estimate of cross-domain contextual bias. Building upon this, a Semantic Augmentation (SA) strategy selectively augments minority and confusable classes through adaptive MixUp in both source-similar and source-dissimilar target regions, improving minority recall without overfitting dominant categories. To stabilize learning under biased pseudo-labels, we design a Semantic-Aware Loss (SAL) that applies diagonally normalized weights, preventing gradient explosion while emphasizing minority majority corrections. Additionally, a frozen Expert branch derived from large vision foundation models (LVFMs) serves as a supervisory reference during training, refining pseudo-label quality without adding inference overhead. GT’s behavior-driven bias quantification makes it broadly applicable across domains without relying on dataset priors. Evaluations on Cityscapes \(\rightarrow \) Foggy (50.8 mAP) and medical transfers (+5.9 AP \(_{50}\) on DDSM \(\rightarrow \) INBreast) show consistent gains and improved minority-class detection, with less than 12% additional training cost. Code and model are available at this link.
