Data-free Dense Depth Distillation. (arXiv:2208.12464v1 [cs.CV])

We study data-free knowledge distillation (KD) for monocular depth estimation
(MDE), which learns a lightweight network for real-world depth perception by
compressing from a trained expert model under the teacher-student framework
while lacking training data in the target domain. Owing to the essential
difference between dense regression and image recognition, previous methods of
data-free KD are not applicable to MDE. To strengthen the applicability in the
real world, in this paper, we seek to apply KD with out-of-distribution
simulated images. …

arxiv cv data distillation free