# Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data

Source: [Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data](<https://www.sota2.com/research/paper/698575dcc97a0b3e3b5d5ec4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-07T05:00:14.331Z

Authors: Sudeepta Mondal, Xinyi Mary Xie, Ruxiao Duan, Alex Wong, Ganesh Sundaramoorthi

Published: 2026-02-05T17:46:40.000Z

## Abstract

Existing out-of-distribution (OOD) detectors are often tuned by a separate dataset deemed OOD with respect to the training distribution of a neural network (NN). OOD detectors process the activations of NN layers and score the output, where parameters of the detectors are determined by fitting to an in-distribution (training) set and the aforementioned dataset chosen adhocly. At detector training time, this adhoc dataset may not be available or difficult to obtain, and even when it's available, it may not be representative of actual OOD data, which is often ''unknown unknowns." Current benchmarks may specify some left-out set from test OOD sets. We show that there can be significant variance in performance of detectors based on the adhoc dataset chosen in current literature, and thus even if such a dataset can be collected, the performance of the detector may be highly dependent on the choice. In this paper, we introduce and formalize the often neglected problem of tuning OOD detectors without a given \`\`OOD'' dataset. To this end, we present strong baselines as an attempt to approach this problem. Furthermore, we propose a new generic approach to OOD detector tuning that does not require any extra data other than those used to train the NN. We show that our approach improves over baseline methods consistently across higher-parameter OOD detector families, while being comparable across lower-parameter families.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Out-of-Distribution Detection on ImageNet-1K ResNet-50 (test)](<https://www.sota2.com/research/sota/out-of-distribution-detection-on-imagenet-1k-resnet-50-test.md>): Out-of-Distribution Detection; ImageNet-1K ResNet-50 (test); Near-OOD AUROC: 78.22.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.05935>)

[PDF](<https://arxiv.org/pdf/2602.05935.pdf>)