Mahalanobis-Aware Training for Out-of-Distribution Detection
While deep learning models have seen widespread success in controlled environments, there are still barriers to their adoption in open-world settings. One critical task for safe deployment is the detection of anomalous or out-of-distribution samples that may require human intervention. In this work, we present a novel loss function and recipe for training networks with improved density-based out-of-distribution sensitivity. We demonstrate the effectiveness of our method on CIFAR-10, notably reducing the false-positive rate of the relative Mahalanobis distance method on far-OOD tasks by over 50%.
Code (0)
등록된 구현이 없습니다.
Tasks
Out-of-Distribution DetectionSensitivitySimilar Papers 제목 키워드 기반
On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imaging
Implementing neural networks for clinical use in medical applications necessitates the ability for the network to detect when input data differs significantly from the training data, with the aim of preventing unreliable…
Out-of-Distribution DetectionOut of Distribution (OOD) DetectionMaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring
Foundation models provide highly descriptive representations for medical images, yet their reliability degrades under distribution shifts arising from changes in patients, devices, or acquisition conditions. Reliable out…
Out-of-Distribution DetectionA Geometry-Based View of Mahalanobis OOD Detection
Out-of-distribution (OOD) detection is critical for reliable deployment of vision models. Mahalanobis-based detectors remain strong baselines, yet their performance varies widely across modern pretrained representations,…
Task Agnostic and Post-hoc Unseen Distribution Detection
Despite the recent advances in out-of-distribution(OOD) detection, anomaly detection, and uncertainty estimation tasks, there do not exist a task-agnostic and post-hoc approach. To address this limitation, we design a no…
Anomaly DetectionOut of Distribution (OOD) DetectionUnsupervised Out-of-Distribution Dialect Detection with Mahalanobis Distance
Dialect classification is used in a variety of applications, such as machine translation and speech recognition, to improve the overall performance of the system. In a real-world scenario, a deployed dialect classificati…
ClassificationDialect IdentificationMachine TranslationMulti-Task Learning+3