On Imagenette and a 1000-image ImageNet sample, learned compression (HiFiC, ELIC) defends image classifiers against adversarial examples better than JPEG, especially for Vision Transformers, and sequential compression rounds add further robustness.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Human Aligned Compression for Robust Models
On Imagenette and a 1000-image ImageNet sample, learned compression (HiFiC, ELIC) defends image classifiers against adversarial examples better than JPEG, especially for Vision Transformers, and sequential compression rounds add further robustness.