Related papers: Identifying and Benchmarking Natural Out-of-Contex…

In real-world applications where confidence is key, like autonomous driving, the accurate detection and appropriate handling of classes differing from those used during training are crucial. Despite the proposal of various unknown object…

Deep neural networks have been successful in diverse discriminative classification tasks, although, they are poorly calibrated often assigning high probability to misclassified predictions. Potential consequences could lead to…

Anomaly detection aims to identify observations that deviate from expected behavior. Because anomalous events are inherently sparse, most frameworks are trained exclusively on normal data to learn a single reference model of normality. This…

Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e.g. meta-learning through long inner loop unrolls or optimizing non-differentiable operators.…

This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen…

Recently there has been a surge of interest in operations research (OR) and the machine learning (ML) community in combining prediction algorithms and optimization techniques to solve decision-making problems in the face of uncertainty.…

The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment. Some recent works tried to investigate semi-supervised…

Predictive models of student success in Massive Open Online Courses (MOOCs) are a critical component of effective content personalization and adaptive interventions. In this article we review the state of the art in predictive models of…

Deep learning (DL)-based systems can exhibit unexpected behavior when exposed to out-of-distribution (OOD) scenarios, posing serious risks in safety-critical domains such as malware detection and autonomous driving. This underscores the…

Object ranking is an important problem in the realm of preference learning. On the basis of training data in the form of a set of rankings of objects, which are typically represented as feature vectors, the goal is to learn a ranking…

Modern digital applications extensively integrate Artificial Intelligence models into their core systems, offering significant advantages for automated decision-making. However, these AI-based systems encounter reliability and safety…

AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic.…

One critical prerequisite for the deployment of reinforcement learning systems in the real world is the ability to reliably detect situations on which the agent was not trained. Such situations could lead to potential safety risks when…

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, which are slightly perturbed input images which lead DNNs to make wrong predictions. To protect from such examples, various defense strategies have been…

Because the choice and tuning of the optimizer affects the speed, and ultimately the performance of deep learning, there is significant past and recent research in this area. Yet, perhaps surprisingly, there is no generally agreed-upon…

Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled…

While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, where the test data come from another distribution (w.r.t. the…

Automated benchmarking environments aim to support researchers in understanding how different algorithms perform on different types of optimization problems. Such comparisons provide insights into the strengths and weaknesses of different…

We study the problem of Out-of-Distribution (OOD) detection, that is, detecting whether a learning algorithm's output can be trusted at inference time. While a number of tests for OOD detection have been proposed in prior work, a formal…

Deep neural networks have attained remarkable performance when applied to data that comes from the same distribution as that of the training set, but can significantly degrade otherwise. Therefore, detecting whether an example is…