Papers › Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond

Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond

22 Jul 2024arXiv:2407.15739archive 2025-07-28

Silvio Galesso, Philipp Schröppel, Hssan Driss, Thomas Brox

In recent years, research on out-of-distribution (OoD) detection for semantic segmentation has mainly focused on road scenes -- a domain with a constrained amount of semantic diversity. In this work, we challenge this constraint and extend the domain of this task to general natural images. To this end, we introduce: 1. the ADE-OoD benchmark, which is based on the ADE20k dataset and includes images from diverse domains with a high semantic diversity, and 2. a novel approach that uses Diffusion score matching for OoD detection (DOoD) and is robust to the increased semantic diversity. ADE-OoD features indoor and outdoor images, defines 150 semantic categories as in-distribution, and contains a variety of OoD objects. For DOoD, we train a diffusion model with an MLP architecture on semantic in-distribution embeddings and build on the score matching interpretation to compute pixel-wise OoD scores at inference time. On common road scene OoD benchmarks, DOoD performs on par or better than the state of the art, without using outliers for training or making assumptions about the data domain. On ADE-OoD, DOoD outperforms previous approaches, but leaves much room for future improvements.

PaperPDFCode

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

Code

lmb-freiburg/diffusion-for-ood officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

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

Tasks

Anomaly DetectionAnomaly SegmentationDiversityOut of Distribution (OOD) DetectionOut-of-Distribution DetectionSemantic Segmentation

Datasets

Introduced by this paper, per the archive.

ADE-OoD

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Anomaly Detection Road Anomaly DOoD AP 89.1 #3 of 10 Archive leaderboard report
Anomaly Detection Road Anomaly DOoD FPR95 8.8 #3 of 10 Archive leaderboard report
Out-of-Distribution Detection ADE-OoD DOoD AP 63.03 #2 of 4 Archive leaderboard report
Out-of-Distribution Detection ADE-OoD DOoD FPR@95 36.50 #2 of 4 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

Diffusion

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