AI RESEARCH
Dual-Teacher Distillation with Subnetwork Rectification for Black-Box Domain Adaptation
arXiv CS.LG
•
ArXi:2603.22908v1 Announce Type: cross Assuming that neither source data nor the source model is accessible, black box domain adaptation represents a highly practical yet extremely challenging setting, as transferable information is restricted to the predictions of the black box source model, which can only be queried using target samples.