Challenges of Adversarial Image Augmentations
Image augmentations applied during training are crucial for the generalization performance of image classifiers. Therefore, a large body of research has focused on finding the optimal augmentation policy for a given task. Yet, RandAugment [2], a simple random augmentation policy, has recently been shown to outperform existing sophisticated policies. Only Adversarial AutoAugment (AdvAA) [11], an approach based on the idea of adversarial training, has shown to be better than RandAugment. In this paper, we show that random augmentations are still competitive compared to an optimal adversarial approach, as well as to simple curricula, and conjecture that the success of AdvAA is due to the stochasticity of the policy controller network, which introduces a mild form of curriculum.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions
Existing object detectors encounter challenges in handling domain shifts between training and real-world data, particularly under poor visibility conditions like fog and night. Cutting-edge cross-domain object detection …
Adversarial Defenseobject-detectionObject DetectionAdversarial Bayesian Augmentation for Single-Source Domain Generalization
Generalizing to unseen image domains is a challenging problem primarily due to the lack of diverse training data, inaccessible target data, and the large domain shift that may exist in many real-world settings. As such d…
Data AugmentationDomain GeneralizationPhoto to Rest GeneralizationSingle-Source Domain GeneralizationThe Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations
To help adversarial examples generalize from surrogate machine-learning (ML) models to targets, certain transferability-based black-box evasion attacks incorporate data augmentations (e.g., random resizing). Yet, prior w…
Adversarial RobustnessData AugmentationAugLy: Data Augmentations for Robustness
We introduce AugLy, a data augmentation library with a focus on adversarial robustness. AugLy provides a wide array of augmentations for multiple modalities (audio, image, text, & video). These augmentations were inspire…
Adversarial RobustnessData AugmentationLearning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks
Unlearnable example attacks are data poisoning techniques that can be used to safeguard public data against unauthorized use for training deep learning models. These methods add stealthy perturbations to the original ima…
Data AugmentationData Poisoning