AugMax: Adversarial Composition of Random Augmentations for Robust Training

• URL: http://arxiv.org/abs/2110.13771v1
• Date: Tue, 26 Oct 2021 15:23:56 GMT
• Title: AugMax: Adversarial Composition of Random Augmentations for Robust Training
• Authors: Haotao Wang, Chaowei Xiao, Jean Kossaifi, Zhiding Yu, Anima Anandkumar, Zhangyang Wang
• Abstract summary: We propose a data augmentation framework, termed AugMax, to unify the two aspects of diversity and hardness. AugMax first randomly samples multiple augmentation operators and then learns an adversarial mixture of the selected operators. Experiments show that AugMax-DuBIN leads to significantly improved out-of-distribution robustness, outperforming prior arts by 3.03%, 3.49%, 1.82% and 0.71%.
• Score: 118.77956624445994
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data augmentation is a simple yet effective way to improve the robustness of deep neural networks (DNNs). Diversity and hardness are two complementary dimensions of data augmentation to achieve robustness. For example, AugMix explores random compositions of a diverse set of augmentations to enhance broader coverage, while adversarial training generates adversarially hard samples to spot the weakness. Motivated by this, we propose a data augmentation framework, termed AugMax, to unify the two aspects of diversity and hardness. AugMax first randomly samples multiple augmentation operators and then learns an adversarial mixture of the selected operators. Being a stronger form of data augmentation, AugMax leads to a significantly augmented input distribution which makes model training more challenging. To solve this problem, we further design a disentangled normalization module, termed DuBIN (Dual-Batch-and-Instance Normalization), that disentangles the instance-wise feature heterogeneity arising from AugMax. Experiments show that AugMax-DuBIN leads to significantly improved out-of-distribution robustness, outperforming prior arts by 3.03%, 3.49%, 1.82% and 0.71% on CIFAR10-C, CIFAR100-C, Tiny ImageNet-C and ImageNet-C. Codes and pretrained models are available: https://github.com/VITA-Group/AugMax.

Related papers

• 3D-VirtFusion: Synthetic 3D Data Augmentation through Generative Diffusion Models and Controllable Editing [52.68314936128752]
  We propose a new paradigm to automatically generate 3D labeled training data by harnessing the power of pretrained large foundation models. For each target semantic class, we first generate 2D images of a single object in various structure and appearance via diffusion models and chatGPT generated text prompts. We transform these augmented images into 3D objects and construct virtual scenes by random composition.
  arXiv  Detail & Related papers  (2024-08-25T09:31:22Z)
• Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training [25.02026393037821]
  We find that SSHPE can be boosted from two cores: advanced data augmentations and concise consistency training ways. We propose to repeatedly augment unlabeled images with diverse hard augmentations, and generate multi-path predictions sequentially. Compared to SOTA approaches, our method brings substantial improvements on public datasets.
  arXiv  Detail & Related papers  (2024-02-18T12:27:59Z)
• DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection [77.6648187359111]
  We propose a novel data augmentation method, named textbfDualAug, to keep the augmentation in distribution as much as possible at a reasonable time and computational cost. Experiments on supervised image classification benchmarks show that DualAug improve various automated data augmentation method.
  arXiv  Detail & Related papers  (2023-10-12T08:55:10Z)
• DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers [6.131022957085439]
  We introduce DiffAug, a simple and efficient diffusion-based augmentation technique to train image classifiers. Applying DiffAug to a given example consists of one forward-diffusion step followed by one reverse-diffusion step.
  arXiv  Detail & Related papers  (2023-06-15T15:19:25Z)
• AugDiff: Diffusion based Feature Augmentation for Multiple Instance Learning in Whole Slide Image [15.180437840817788]
  Multiple Instance Learning (MIL), a powerful strategy for weakly supervised learning, is able to perform various prediction tasks on gigapixel Whole Slide Images (WSIs) We introduce the Diffusion Model (DM) into MIL for the first time and propose a feature augmentation framework called AugDiff. We conduct extensive experiments over three distinct cancer datasets, two different feature extractors, and three prevalent MIL algorithms to evaluate the performance of AugDiff.
  arXiv  Detail & Related papers  (2023-03-11T10:36:27Z)
• Soft Augmentation for Image Classification [68.71067594724663]
  We propose generalizing augmentation with invariant transforms to soft augmentation. We show that soft targets allow for more aggressive data augmentation. We also show that soft augmentations generalize to self-supervised classification tasks.
  arXiv  Detail & Related papers  (2022-11-09T01:04:06Z)
• SelectAugment: Hierarchical Deterministic Sample Selection for Data Augmentation [72.58308581812149]
  We propose an effective approach, dubbed SelectAugment, to select samples to be augmented in a deterministic and online manner. Specifically, in each batch, we first determine the augmentation ratio, and then decide whether to augment each training sample under this ratio. In this way, the negative effects of the randomness in selecting samples to augment can be effectively alleviated and the effectiveness of DA is improved.
  arXiv  Detail & Related papers  (2021-12-06T08:38:38Z)
• Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models [51.46732511844122]
  Powerful pre-trained language models (PLM) can be fooled by small perturbations or intentional attacks. We present Virtual Data Augmentation (VDA), a general framework for robustly fine-tuning PLMs. Our approach is able to improve the robustness of PLMs and alleviate the performance degradation under adversarial attacks.
  arXiv  Detail & Related papers  (2021-09-13T09:15:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.