3 papers
cs.CV2026
LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation
Jing Li, Pan Liu, Meng Zhao +7
Source-free universal domain adaptation (SF-UniDA) adapts a pre-trained source model to an unlabeled target domain under both covariate and label shifts, without access to source d…
cs.CV2026
Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation
Zhe Zhang, Jing Li, Wanli Xue +4
Assuming that neither source data nor source model parameters are accessible, black-box domain adaptation (BBDA) represents a highly practical yet challenging setting, where transf…
cs.CV2024
Can Students Beyond The Teacher? Distilling Knowledge from Teacher's Bias
Jianhua Zhang, Yi Gao, Ruyu Liu +3
Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing met…