Papers › Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data

Dense Out-of-Distribution Detection by Robust Learning on Synthetic Negative Data

23 Dec 2021arXiv:2112.12833archive 2025-07-28

Matej Grcić, Petra Bevandić, Zoran Kalafatić, Siniša Šegvić

Standard machine learning is unable to accommodate inputs which do not belong to the training distribution. The resulting models often give rise to confident incorrect predictions which may lead to devastating consequences. This problem is especially demanding in the context of dense prediction since input images may be only partially anomalous. Previous work has addressed dense out-of-distribution detection by discriminative training with respect to off-the-shelf negative datasets. However, real negative data are unlikely to cover all modes of the entire visual world. To this end, we extend this approach by generating synthetic negative patches along the border of the inlier manifold. We leverage a jointly trained normalizing flow due to coverage-oriented learning objective and the capability to generate samples at different resolutions. We detect anomalies according to a principled information-theoretic criterion which can be consistently applied through training and inference. The resulting models set the new state of the art on benchmarks for out-of-distribution detection in road-driving scenes and remote sensing imagery, in spite of minimal computational overhead.

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 DetectionOut-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Fishyscapes L&F NFlowJS-GF (with extra inlier set: Vistas and Wilddash2) AP 69.43 #2 of 18 Archive leaderboard report
Anomaly Detection Fishyscapes L&F NFlowJS-GF (with extra inlier set: Vistas and Wilddash2) FPR95 2.00 #2 of 18 Archive leaderboard report
Anomaly Detection Fishyscapes L&F NFlow AP 39.36 #11 of 18 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

Normalizing Flows

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