De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts

arXiv:2403.19539v1 Announce Type: new
Abstract: Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by utilizing synthetic or sampled data. However, a long-overlooked issue is that the severe distribution shifts between their substitution and original data, which manifests as huge differences in the quality of images and class proportions. The harmful shifts are essentially the confounder that …

abstract arxiv cs.cv data deployment distillation distribution free however issue knowledge performance private data small synthetic train training training data type