DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers for the crucial yet challenging goal of improved classifier robustness. Applying DiffAug to a given example consists of one forward-diffusion step followed by one reverse-diffusion step. Using both ResNet-50 and Vision Transformer architectures, we comprehensively evaluate classifiers trained with DiffAug and demonstrate the surprising effectiveness of single-step reverse diffusion in improving robustness to covariate shifts, certified adversarial accuracy and out of distribution detection. When we combine DiffAug with other augmentations such as AugMix and DeepAugment we demonstrate further improved robustness. Finally, building on this approach, we also improve classifier-guided diffusion wherein we observe improvements in: (i) classifier-generalization, (ii) gradient quality (i.e., improved perceptual alignment) and (iii) image generation performance. We thus introduce a computationally efficient technique for training with improved robustness that does not require any additional data, and effectively complements existing augmentation approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingImage GenerationOut-of-Distribution DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
Unsupervised Contrastive learning has gained prominence in fields such as vision, and biology, leveraging predefined positive/negative samples for representation learning. Data augmentation, categorized into hand-designe…
Contrastive LearningData AugmentationImage ClassificationRepresentation LearningDifferentiable Augmentation for Data-Efficient GAN Training
The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminator is memorizing the exact training set. To combat it, we prop…
Image GenerationMedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentatio
Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification. Conventional augmentation can improve training diversity but may distort diagnostically i…
Medical Image ClassificationImage AugmentationDiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising
Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models,…
Adversarial DefenseDenoisingPC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner
Autonomous driving in complex traffic requires planners that generalize beyond hand-crafted rules, motivating data-driven approaches that learn behavior from expert demonstrations. Diffusion-based trajectory planners hav…
Autonomous Driving