Search Results for author:
Found 7 papers, 5 papers with code
Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization
Specifically, we design a novel method, termed Abnormal Adversarial Examples Regularization (AAER), which explicitly regularizes the variation of AAEs to hinder the classifier from becoming distorted.
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting.
On the Onset of Robust Overfitting in Adversarial Training
Adversarial Training (AT) is a widely-used algorithm for building robust neural networks, but it suffers from the issue of robust overfitting, the fundamental mechanism of which remains unclear.
Strength-Adaptive Adversarial Training
Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum.
Understanding Robust Overfitting of Adversarial Training and Beyond
Here, we explore the causes of robust overfitting by comparing the data distribution of \emph{non-overfit} (weak adversary) and \emph{overfitted} (strong adversary) adversarial training, and observe that the distribution of the adversarial data generated by weak adversary mainly contain small-loss data.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
Hierarchical Bilinear Pooling for Fine-Grained Visual Recognition
Fine-grained visual recognition is challenging because it highly relies on the modeling of various semantic parts and fine-grained feature learning.
