Papers › Shifting Transformation Learning for Out-of-Distribution Detection

Shifting Transformation Learning for Out-of-Distribution Detection

7 Jun 2021arXiv:2106.03899archive 2025-07-28

Sina Mohseni, Arash Vahdat, Jay Yadawa

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Recently, self-supervised representation learning techniques (via contrastive learning and pretext learning) have shown effective in improving OOD detection. However, one major issue with such approaches is the choice of shifting transformations and pretext tasks which depends on the in-domain distribution. In this paper, we propose a simple framework that leverages a shifting transformation learning setting for learning multiple shifted representations of the training set for improved OOD detection. To address the problem of selecting optimal shifting transformation and pretext tasks, we propose a simple mechanism for automatically selecting the transformations and modulating their effect on representation learning without requiring any OOD training samples. In extensive experiments, we show that our simple framework outperforms state-of-the-art OOD detection models on several image datasets. We also characterize the criteria for a desirable OOD detector for real-world applications and demonstrate the efficacy of our proposed technique against state-of-the-art OOD detection techniques.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionContrastive LearningOut of Distribution (OOD) DetectionOut-of-Distribution DetectionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection One-class CIFAR-100 MTL AUROC 83.95 #11 of 15 Archive leaderboard report
Anomaly Detection Unlabeled CIFAR-10 vs CIFAR-100 MTL AUROC 82.92 #9 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections