Related papers: rSDNet: Unified Robust Neural Learning against Lab…
Adversarial attacks have been shown to be highly effective at degrading the performance of deep neural networks (DNNs). The most prominent defense is adversarial training, a method for learning a robust model. Nevertheless, adversarial…
Because large, human-annotated datasets suffer from labeling errors, it is crucial to be able to train deep neural networks in the presence of label noise. While training image classification models with label noise have received much…
Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to…
We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise,…
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is…
Successful training of deep neural networks with noisy labels is an essential capability as most real-world datasets contain some amount of mislabeled data. Left unmitigated, label noise can sharply degrade typical supervised learning…
In recent years, the remarkable success of deep neural networks (DNNs) in computer vision is largely due to large-scale, high-quality labeled datasets. Training directly on real-world datasets with label noise may result in overfitting. The…
To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the…
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization…
Although deep face recognition benefits significantly from large-scale training data, a current bottleneck is the labelling cost. A feasible solution to this problem is semi-supervised learning, exploiting a small portion of labelled data…
We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness…
Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…
The robustness of supervised deep learning-based medical image classification is significantly undermined by label noise. Although several methods have been proposed to enhance classification performance in the presence of noisy labels,…
The robustness of deep neural networks is usually lacking under adversarial examples, common corruptions, and distribution shifts, which becomes an important research problem in the development of deep learning. Although new deep learning…
Node classification on graphs is a significant task with a wide range of applications, including social analysis and anomaly detection. Even though graph neural networks (GNNs) have produced promising results on this task, current…
Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the…
State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to label errors in this data, typically resulting in large efforts and costs and therefore…
Feature noise and label noise are ubiquitous in practical scenarios, which pose great challenges for training a robust machine learning model. Most previous approaches usually deal with only a single problem of either feature noise or label…
Deep neural networks trained on large supervised datasets have led to impressive results in image classification and other tasks. However, well-annotated datasets can be time-consuming and expensive to collect, lending increased interest to…
Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…