Related papers: Rich Feature Construction for the Optimization-Gen…

Out-of-distribution (OOD) generalization remains a fundamental challenge in real-world classification, where test distributions often differ substantially from training data. Most existing approaches pursue domain-invariant representations,…

In real-world applications, machine learning models must reliably detect Out-of-Distribution (OoD) samples to prevent unsafe decisions. Current OoD detection methods often rely on analyzing the logits or the embeddings of the penultimate…

Oblique Decision Tree (ODT) separates the feature space by linear projections, as opposed to the conventional Decision Tree (DT) that forces axis-parallel splits. ODT has been proven to have a stronger representation ability than DT, as it…

Addressing the Out-of-Distribution (OoD) segmentation task is a prerequisite for perception systems operating in an open-world environment. Large foundational models are frequently used in downstream tasks, however, their potential for OoD…

Out-of-Distribution (OoD) detection is important for building safe artificial intelligence systems. However, current OoD detection methods still cannot meet the performance requirements for practical deployment. In this paper, we propose a…

Out-of-Distribution (OOD) generalization, a cornerstone for building robust machine learning models capable of handling data diverging from the training set's distribution, is an ongoing challenge in deep learning. While significant…

Graphs are a fundamental data structure for representing relational information in domains such as social networks, molecular systems, and knowledge graphs. However, graph learning models often suffer from limited generalization when…

Fair classification and fair representation learning are two important problems in supervised and unsupervised fair machine learning, respectively. Fair classification asks for a classifier that maximizes accuracy on a given data…

Deep Learning models are easily disturbed by variations in the input images that were not observed during the training stage, resulting in unpredictable predictions. Detecting such Out-of-Distribution (OOD) images is particularly crucial in…

We consider the problem of reinforcement learning over episodes of a finite-horizon deterministic system and as a solution propose optimistic constraint propagation (OCP), an algorithm designed to synthesize efficient exploration and value…

Advancements in synthesized speech have created a growing threat of impersonation, making it crucial to develop deepfake algorithm recognition. One significant aspect is out-of-distribution (OOD) detection, which has gained notable…

State-of-the-art image classifiers trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental distribution shifts. On the other hand, several recent classifiers with…

Deep learning models are increasingly deployed in safety-critical applications, where reliable out-of-distribution (OOD) detection is essential to ensure robustness. Existing methods predominantly rely on the penultimate-layer activations…

Models trained on one set of domains often suffer performance drops on unseen domains, e.g., when wildlife monitoring models are deployed in new camera locations. In this work, we study principles for designing data augmentations for…

Most approaches to out-of-distribution (OOD) generalization learn domain-invariant representations by discarding contextual bias. In this paper, we raise a critical question: Should bias be eliminated? If not, is there a general way to…

For classification problems, feature extraction is a crucial process which aims to find a suitable data representation that increases the performance of the machine learning algorithm. According to the curse of dimensionality theorem, the…

In this work, we train a network to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected. This is made possible by leveraging an OoD…

Out-of-distribution (OOD) detection is crucial when deploying deep neural networks in the real world to ensure the reliability and safety of their applications. One main challenge in OOD detection is that neural network models often produce…

One of the early weaknesses identified in deep neural networks trained for image classification tasks was their inability to provide low confidence predictions on out-of-distribution (OOD) data that was significantly different from the…

Deep networks often exhibit a preference for "simple" solutions, and such a simplicity bias is widely believed to play a key role in generalization. Yet a broadly applicable, quantitative measure of simplicity remains elusive. We introduce…