The reviewed record of science sign in
Pith

arxiv: 2007.05566 · v1 · pith:WDLASH5T · submitted 2020-07-10 · cs.LG · stat.ML

Contrastive Training for Improved Out-of-Distribution Detection

Jim Winkens , Rudy Bunel , Abhijit Guha Roy , Robert Stanforth , Vivek Natarajan , Joseph R. Ledsam , Patricia MacWilliams , Pushmeet Kohli
show 5 more authors
Alan Karthikesalingam Simon Kohl Taylan Cemgil S. M. Ali Eslami Olaf Ronneberger
This is my paper

Reviewed by Pithpith:WDLASH5Topen to challenge →

classification cs.LG stat.ML
keywords detectioncontrastiveperformancetrainingmethodsout-of-distributionaccessapproach
0
0 comments X
read the original abstract

Reliable detection of out-of-distribution (OOD) inputs is increasingly understood to be a precondition for deployment of machine learning systems. This paper proposes and investigates the use of contrastive training to boost OOD detection performance. Unlike leading methods for OOD detection, our approach does not require access to examples labeled explicitly as OOD, which can be difficult to collect in practice. We show in extensive experiments that contrastive training significantly helps OOD detection performance on a number of common benchmarks. By introducing and employing the Confusion Log Probability (CLP) score, which quantifies the difficulty of the OOD detection task by capturing the similarity of inlier and outlier datasets, we show that our method especially improves performance in the `near OOD' classes -- a particularly challenging setting for previous methods.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Rethinking Vacuity for OOD Detection in Evidential Deep Learning

    cs.AI 2026-05 accept novelty 7.0

    Vacuity-based OOD detection in evidential deep learning is highly sensitive to class cardinality differences between ID and OOD, which can artificially inflate AUROC and AUPR without any change in model predictions.

  2. Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition

    cs.CV 2026-06 unverdicted novelty 6.0

    A modality-aware post-hoc detector for multi-modal OOD detection in action recognition combines uni-modal prediction relationships with feature-space scores and outperforms prior methods on the MultiOOD benchmark.

  3. Language Models (Mostly) Know What They Know

    cs.CL 2022-07 unverdicted novelty 6.0

    Language models show good calibration when asked to estimate the probability that their own answers are correct, with performance improving as models get larger.

  4. Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection

    cs.LG 2026-05 unverdicted novelty 5.0

    Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.

  5. Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift

    cs.LG 2026-04 unverdicted novelty 5.0

    JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.