MCAT improves adversarial robustness on long-tailed datasets by constraining examples to class manifolds and enforcing balanced geometric separation.
Adversarial weight perturbation helps robust gener- alization.Advances in neural information processing sys- tems, 33:2958–2969,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment
MCAT improves adversarial robustness on long-tailed datasets by constraining examples to class manifolds and enforcing balanced geometric separation.