AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation

arXiv:2403.07030v1 Announce Type: new
Abstract: Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation (DFKD) methods have emerged as direct solutions. However, simply adopting models derived from DFKD for real-world applications suffers significant performance degradation, due to the discrepancy between teachers' training data and real-world scenarios (student domain). The degradation stems from the portions of teachers' …

anchor arxiv cs.cv cs.lg distillation domain domain knowledge knowledge type