An asymmetric multi-level distillation framework lets a student ViT approximate clean-image representations from distorted inputs alone, outperforming prior methods on classification under distortions.
In: International Conference on Learning Representations (2018)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
citing papers explorer
-
Distilling Vision Transformers for Distortion-Robust Representation Learning
An asymmetric multi-level distillation framework lets a student ViT approximate clean-image representations from distorted inputs alone, outperforming prior methods on classification under distortions.