SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANs. (arXiv:2208.04226v2 [cs.CV] UPDATED)

With the usage of appropriate inductive biases, Counterfactual Generative
Networks (CGNs) can generate novel images from random combinations of shape,
texture, and background manifolds. These images can be utilized to train an
invariant classifier, avoiding the wide spread problem of deep architectures
learning spurious correlations rather than meaningful ones. As a consequence,
out-of-domain robustness is improved. However, the CGN architecture comprises
multiple over parameterized networks, namely BigGAN and U2-Net. Training these
networks requires appropriate background knowledge and extensive computation.
Since …

arxiv cv distillation free knowledge networks