Pith. sign in

Boosting adversarial training with hypersphere embedding,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2024 1

verdicts

REJECT 1

representative citing papers

Learning Fair Robustness via Domain Mixup

cs.LG · 2024-11-21 · reject · novelty 3.0

A claim that same-class mixup combined with adversarial training provably reduces class-wise robustness disparity, but the theoretical support is invalid because it evaluates the classifier on the wrong distribution and uses incorrect Phi-difference formulas.

citing papers explorer

Showing 1 of 1 citing paper.

  • Learning Fair Robustness via Domain Mixup cs.LG · 2024-11-21 · reject · none · ref 5

    A claim that same-class mixup combined with adversarial training provably reduces class-wise robustness disparity, but the theoretical support is invalid because it evaluates the classifier on the wrong distribution and uses incorrect Phi-difference formulas.