Search Results for author:
Found 2 papers, 1 papers with code
Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay
In particular, we design a Variational Autoencoder (VAE) with a training objective that is customized to learn the synthetic data representations optimally.
Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data
Moreover, the sample generation strategies in some of these methods could result in a mismatch between the synthetic and real data distributions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
