Add to ORKGSemi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, three recent SSL algorithms with SCAR result in significantly improved image classification.Comment: 4 page
International audienceDespite their performance, Artificial Neural Networks are not reliable enough ...
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in levera...
We propose a new data augmentation technique for semi-supervised learning settings that emphasizes l...
Adversarial robustness is a research area that has recently received a lot of attention in the quest...
Emerging self-supervised learning (SSL) has become a popular image representation encoding method to...
Semi-supervised learning (SSL) is the branch of machine learning that aims to improve learning perfo...
Deep learning plays an important role in various disciplines, such as auto-driving, information tech...
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increas...
Supervised learning has been widely used for attack categorization, requiring high-quality data and ...
Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the...
In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between...
Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ on...
Self-supervised learning (SSL) has emerged as a promising alternative to create supervisory signals ...
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for ...
The threat of data-poisoning backdoor attacks on learning algorithms typically comes from the labele...
International audienceDespite their performance, Artificial Neural Networks are not reliable enough ...
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in levera...
We propose a new data augmentation technique for semi-supervised learning settings that emphasizes l...
Adversarial robustness is a research area that has recently received a lot of attention in the quest...
Emerging self-supervised learning (SSL) has become a popular image representation encoding method to...
Semi-supervised learning (SSL) is the branch of machine learning that aims to improve learning perfo...
Deep learning plays an important role in various disciplines, such as auto-driving, information tech...
Following the success of supervised learning, semi-supervised learning (SSL) is now becoming increas...
Supervised learning has been widely used for attack categorization, requiring high-quality data and ...
Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the...
In the field of machine learning, semi-supervised learning (SSL) occupies the middle ground, between...
Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ on...
Self-supervised learning (SSL) has emerged as a promising alternative to create supervisory signals ...
Adversarial training (AT) for robust representation learning and self-supervised learning (SSL) for ...
The threat of data-poisoning backdoor attacks on learning algorithms typically comes from the labele...
International audienceDespite their performance, Artificial Neural Networks are not reliable enough ...
State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in levera...
We propose a new data augmentation technique for semi-supervised learning settings that emphasizes l...