Related papers: Virtual Adversarial Training: A Regularization Met…
Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…
We consider a semi-supervised classification problem with non-stationary label-shift in which we observe a labelled data set followed by a sequence of unlabelled covariate vectors in which the marginal probabilities of the class labels may…
Most of the current supervised automatic music transcription (AMT) models lack the ability to generalize. This means that they have trouble transcribing real-world music recordings from diverse musical genres that are not presented in the…
Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or…
We introduce ANTIDOTE, a new class of objectives for learning under noisy labels which are defined in terms of a relaxation over an information-divergence neighborhood. Using convex duality, we provide a reformulation as an adversarial…
In the context of noisy partial label learning (NPLL), each training sample is associated with a set of candidate labels annotated by multiple noisy annotators. With the emergence of high-performance pre-trained vision-language models…
Adversarial training methods are state-of-the-art (SOTA) empirical defense methods against adversarial examples. Many regularization methods have been proven to be effective with the combination of adversarial training. Nevertheless, such…
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfitting, i.e., the robustness starts to decrease significantly…
We present a new method to learn video representations from large-scale unlabeled video data. Ideally, this representation will be generic and transferable, directly usable for new tasks such as action recognition and zero or few-shot…
Supervised learning usually requires a large amount of labelled data. However, attaining ground-truth labels is costly for many tasks. Alternatively, weakly supervised methods learn with cheap weak signals that only approximately label some…
Sharpness-Aware Minimization (SAM) is an effective method for improving generalization ability by regularizing loss sharpness. In this paper, we explore SAM in the context of adversarial robustness. We find that using only SAM can achieve…
We study the problem of unsupervised domain adaptation which aims to adapt models trained on a labeled source domain to a completely unlabeled target domain. Recently, the cluster assumption has been applied to unsupervised domain…
Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…
Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of…
Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…
The success of supervised learning hinges on the assumption that the training and test data come from the same underlying distribution, which is often not valid in practice due to potential distribution shift. In light of this, most…
Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets,…
Labeling data via rules-of-thumb and minimal label supervision is central to Weak Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced learning and semi-supervised ensemble learning. By using this labeled data…
We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation. Adversarial training is commonly used for learning domain-invariant representations by reversing the…
Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data…