CVApr 21, 2022

Fast AdvProp

Berkeley
arXiv:2204.09838v110 citationsh-index: 134Has Code
Originality Incremental advance
AI Analysis

This work addresses a computational bottleneck in adversarial training for computer vision researchers, offering an incremental improvement to make AdvProp more practical.

The paper tackles the slow training speed of Adversarial Propagation (AdvProp) by introducing Fast AdvProp, which simplifies training components to make it nearly as cheap as vanilla training while improving model performance on various visual benchmarks without extra cost.

Adversarial Propagation (AdvProp) is an effective way to improve recognition models, leveraging adversarial examples. Nonetheless, AdvProp suffers from the extremely slow training speed, mainly because: a) extra forward and backward passes are required for generating adversarial examples; b) both original samples and their adversarial counterparts are used for training (i.e., 2$\times$ data). In this paper, we introduce Fast AdvProp, which aggressively revamps AdvProp's costly training components, rendering the method nearly as cheap as the vanilla training. Specifically, our modifications in Fast AdvProp are guided by the hypothesis that disentangled learning with adversarial examples is the key for performance improvements, while other training recipes (e.g., paired clean and adversarial training samples, multi-step adversarial attackers) could be largely simplified. Our empirical results show that, compared to the vanilla training baseline, Fast AdvProp is able to further model performance on a spectrum of visual benchmarks, without incurring extra training cost. Additionally, our ablations find Fast AdvProp scales better if larger models are used, is compatible with existing data augmentation methods (i.e., Mixup and CutMix), and can be easily adapted to other recognition tasks like object detection. The code is available here: https://github.com/meijieru/fast_advprop.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes