Adversarial AutoMixup

Abstract

Data mixing augmentation has been widely applied to improve the generalization ability of deep neural networks. Recently, offline data mixing augmentation, e.g. handcrafted and saliency information-based mixup, has been gradually replaced by automatic mixing approaches. Through minimizing two sub-tasks, namely, mixed sample generation and mixup classification in an end-to-end way, AutoMix significantly improves accuracy on image classification tasks. However, as the optimization objective is consistent for the two sub-tasks, this approach is prone to generating consistent instead of diverse mixed samples, which results in overfitting for target task training. In this paper, we propose AdAutomixup, an adversarial automatic mixup augmentation approach that generates challenging samples to train a robust classifier for image classification, by alternatively optimizing the classifier and the mixup sample generator. AdAutomixup comprises two modules, a mixed example generator, and a target classifier. The mixed sample generator aims to produce hard mixed examples to challenge the target classifier, while the target classifier's aim is to learn robust features from hard mixed examples to improve generalization. To prevent the collapse of the inherent meanings of images, we further introduce an exponential moving average (EMA) teacher and cosine similarity to train AdAutomixup in an end-to-end way. Extensive experiments on seven image benchmarks consistently prove that our approach outperforms the state of the art in various classification scenarios. The source code is available at https://github.com/JinXins/Adversarial-AutoMixup.

ICLR 2024 Camera Ready.(19 pages) with the source code at https://github.com/JinXins/Adversarial-AutoMixup

References in corpus (19)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• YOLOv4: Optimal Speed and Accuracy of Object Detection
• Explaining and Harnessing Adversarial Examples
• Improved Regularization of Convolutional Neural Networks with Cutout
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• Intriguing Properties of Vision Transformers
• Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness
• ResizeMix: Mixing Data with Preserved Object Information and True Labels
• MogaNet: Multi-order Gated Aggregation Network
• Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
• Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
• TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
• Harnessing Hard Mixed Samples with Decoupled Regularizer
• SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness
• RecursiveMix: Mixed Learning with History
• SemiReward: A General Reward Model for Semi-supervised Learning
• OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
• MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
• SMMix: Self-Motivated Image Mixing for Vision Transformers