ALFA: Adversarial Feature Augmentation for Enhanced Image Recognition

Tianlong Chen, Yu Cheng, Zhe Gan, Yu Hu, Zhangyang Wang, Jingjing Liu

Keywords: Adversarial Training, Image Recognition, Generalization

Abstract: Adversarial training is an effective method to combat adversarial attacks in order to create robust neural networks. By using an auxiliary batch normalization on adversarial examples, it has been shown recently to possess great potential in improving the generalization ability of neural networks for image recognition as well. However, crafting pixel-level adversarial perturbations is computationally expensive. To address this issue, we propose AdversariaL Feature Augmentation (ALFA), which advocates adversarial training on the intermediate layers of feature embeddings. ALFA utilizes both clean and adversarial augmented features jointly to enhance standard trained networks. To eliminate laborious tuning of key parameters such as locations and strength of feature augmentations, we further design a learnable adversarial feature augmentation (L-ALFA) framework to automatically adjust the perturbation magnitude of each perturbed feature. Extensive experiments demonstrate that our proposed ALFA and L-ALFA methods achieve significant and consistent generalization improvement over strong baselines on CIFAR-10, CIFAR-100, and ImageNet benchmarks across different backbone networks for image recognition.

One-sentence Summary: Utilizing clean and adversarial augmented features to improve the generalization of image recognition

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=igKM4pRijH