Related papers: MEMO: Test Time Robustness via Adaptation and Augm…

Despite their recent success, deep neural networks continue to perform poorly when they encounter distribution shifts at test time. Many recently proposed approaches try to counter this by aligning the model to the new distribution prior to…

The performance of machine learning models under distribution shift has been the focus of the community in recent years. Most of current methods have been proposed to improve the robustness to distribution shift from the algorithmic…

Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used…

A recent trend in deep learning algorithms has been towards training large scale models, having high parameter count and trained on big dataset. However, robustness of such large scale models towards real-world settings is still a…

Deep neural networks often exhibit poor performance on data that is unlikely under the train-time data distribution, for instance data affected by corruptions. Previous works demonstrate that test-time adaptation to data shift, for instance…

Deep neural networks have demonstrated impressive performance in various machine learning tasks. However, they are notoriously sensitive to changes in data distribution. Often, even a slight change in the distribution can lead to drastic…

Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the biomedical field, their performance can be affected by…

With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models. This requires a thorough look not only at the accuracy of such…

Machine learning algorithms have achieved remarkable success across various disciplines, use cases and applications, under the prevailing assumption that training and test samples are drawn from the same distribution. Consequently, these…

Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference,…

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important for deep models when the test environment…

A fundamental assumption of most machine learning algorithms is that the training and test data are drawn from the same underlying distribution. However, this assumption is violated in almost all practical applications: machine learning…

Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…

Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the…

We propose a method for adapting neural networks to distribution shifts at test-time. In contrast to training-time robustness mechanisms that attempt to anticipate and counter the shift, we create a closed-loop system and make use of a…

Most unsupervised anomaly detection methods based on representations of normal samples to distinguish anomalies have recently made remarkable progress. However, existing methods only learn a single decision boundary for distinguishing the…

We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

Training a deep neural network (DNN) often involves stochastic optimization, which means each run will produce a different model. Several works suggest this variability is negligible when models have the same performance, which in the case…

Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…