</> Code with Papers by Syntology

Papers › Out-of-distribution Detection with Implicit Outlier Transformation

Out-of-distribution Detection with Implicit Outlier Transformation

9 Mar 2023arXiv:2303.05033archive 2025-07-28

Qizhou Wang, Junjie Ye, Feng Liu, Quanyu Dai, Marcus Kalander, Tongliang Liu, Jianye Hao, Bo Han

Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typically deviate from test OOD data. Thus, the performance of OE, when facing unseen OOD data, can be weakened. To address this issue, we propose a novel OE-based approach that makes the model perform well for unseen OOD situations, even for unseen OOD cases. It leads to a min-max learning scheme -- searching to synthesize OOD data that leads to worst judgments and learning from such OOD data for uniform performance in OOD detection. In our realization, these worst OOD data are synthesized by transforming original surrogate ones. Specifically, the associated transform functions are learned implicitly based on our novel insight that model perturbation leads to data transformation. Our methodology offers an efficient way of synthesizing OOD data, which can further benefit the detection model, besides the surrogate OOD data. We conduct extensive experiments under various OOD detection setups, demonstrating the effectiveness of our method against its advanced counterparts.

PaperPDFCode

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

Code

qizhouwang/doe officialmentioned in paperpytorch 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

Out-of-Distribution Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection ImageNet-1k vs Curated OODs (avg.) DOE AUROC 83.54 #14 of 16 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Curated OODs (avg.) DOE FPR95 59.83 #14 of 16 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Places DOE AUROC 83.05 #20 of 25 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Places DOE FPR95 67.84 #20 of 25 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs SUN DOE AUROC 76.26 #21 of 22 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs SUN DOE FPR95 80.94 #21 of 22 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures DOE AUROC 88.9 #20 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs Textures DOE FPR95 34.67 #20 of 34 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist DOE AUROC 85.98 #23 of 28 Archive leaderboard report
Out-of-Distribution Detection ImageNet-1k vs iNaturalist DOE FPR95 55.87 #23 of 28 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

Test

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