A lightweight post-hoc adapter trained with an anchored least-squares loss can make a frozen pretrained vision encoder approximately rotation- and noise-invariant with little damage to its original feature space.
Wasserstein distributional robustness of neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Post-Training Augmentation Invariance
A lightweight post-hoc adapter trained with an anchored least-squares loss can make a frozen pretrained vision encoder approximately rotation- and noise-invariant with little damage to its original feature space.