paper-with-me

Papers

Challenges of Adversarial Image Augmentations

2021-11-24 · NeurIPS Workshop ICBINB 2021 12 · Arno Blaas, Xavier Suau, Jason Ramapuram, Nicholas Apostoloff, Luca Zappella

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.

📄 PDF Abstract BibTeX arXiv:2111.12427

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
AutoAugment 설명 없음
RandAugment 설명 없음

Similar Papers 제목 키워드 기반

Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions

2024-03-23 · Kaiwen Wang, Yinzhe Shen, Martin Lauer

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 Detection

Adversarial Bayesian Augmentation for Single-Source Domain Generalization

2023-07-18 · ICCV 2023 1 · Sheng Cheng, Tejas Gokhale, Yezhou Yang

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 Generalization

The Ultimate Combo: Boosting Adversarial Example Transferability by Composing Data Augmentations

2023-12-18 · Zebin Yun, Achi-Or Weingarten, Eyal Ronen, Mahmood Sharif

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 Augmentation

AugLy: Data Augmentations for Robustness

2022-01-17 · Zoe Papakipos, Joanna Bitton

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 Augmentation

Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks

2023-03-27 · Tianrui Qin, Xitong Gao, Juanjuan Zhao, Kejiang Ye 외

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