DBG mitigates boundary overlap in long-tailed learning by generating near-boundary samples, leading to better tail class accuracy and more separable decision spaces.
Boosting adversarial at- tacks with momentum
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
DDG dynamically adjusts perturbation magnitude and supervision strength in fast adversarial training according to sample confidence at the ground-truth class, mitigating catastrophic overfitting and the robustness-accuracy trade-off.
citing papers explorer
-
Decision Boundary-aware Generation for Long-tailed Learning
DBG mitigates boundary overlap in long-tailed learning by generating near-boundary samples, leading to better tail class accuracy and more separable decision spaces.
-
Mitigating Error Amplification in Fast Adversarial Training
DDG dynamically adjusts perturbation magnitude and supervision strength in fast adversarial training according to sample confidence at the ground-truth class, mitigating catastrophic overfitting and the robustness-accuracy trade-off.