rRCM, a contrastive denoising pre-training and fine-tuning scheme, gives a single-pass robust classifier that beats diffusion-based defenses on ImageNet and CIFAR-10 while reducing inference cost by up to 85x.
An empirical study of training self-supervised vision transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Robust Representation Consistency Model via Contrastive Denoising
rRCM, a contrastive denoising pre-training and fine-tuning scheme, gives a single-pass robust classifier that beats diffusion-based defenses on ImageNet and CIFAR-10 while reducing inference cost by up to 85x.