Výsledky vyhledávání

Report

AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

Autor: Yang, Suorong, Li, Jinqiao, Zhao, Jian, Shen, Furao

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical factor that affects on the generalization ability of image classifica

Externí odkaz: http://arxiv.org/abs/2211.16040

Zobrazit plný text záznamu

Report

Minimizing the Ground Effect for Photophoretically Levitating Disks

Autor: Lu, Zhipeng, Stern, Miranda, Li, Jinqiao, Candia, David, Yao-Bate, Lorenzo, Celenza, Thomas J., Azadi, Mohsen, Campbell, Matthew F., Bargatin, Igor

Photophoretic levitation is a propulsion mechanism in which lightweight objects can be lifted and controlled through their interactions with light. Since photophoretic forces on macroscopic objects are usually maximized at low pressures, they may be

Externí odkaz: http://arxiv.org/abs/2209.00745

Zobrazit plný text záznamu

Report

AutoAdversary: A Pixel Pruning Method for Sparse Adversarial Attack

Autor: Li, Jinqiao, Liu, Xiaotao, Zhao, Jian, Shen, Furao

Deep neural networks (DNNs) have been proven to be vulnerable to adversarial examples. A special branch of adversarial examples, namely sparse adversarial examples, can fool the target DNNs by perturbing only a few pixels. However, many existing spar

Externí odkaz: http://arxiv.org/abs/2203.09756

Zobrazit plný text záznamu