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.
Imagenet: A large-scale hierarchical image database
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
UNIV introduces Patch Cross-modal Contrastive Learning (PCCL) to build a unified semantic feature space for infrared and visible modalities, supported by the new MVIP dataset of 98,992 aligned pairs, with reported gains on infrared segmentation and detection tasks.
citing papers explorer
-
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.
-
UNIV: Unified Foundation Model for Infrared and Visible Modalities
UNIV introduces Patch Cross-modal Contrastive Learning (PCCL) to build a unified semantic feature space for infrared and visible modalities, supported by the new MVIP dataset of 98,992 aligned pairs, with reported gains on infrared segmentation and detection tasks.