Out-of-Distribution Detection

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

53 leaderboard tables shown for this task, 53 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 53 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

24 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 438 papers with code (888 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
  13 May 2019 30 repositories listed Syntology ran 17 of 24 samples · 7 unverified · 5 pointer-only (licence)
  Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
  7 Oct 2016 14 repositories listed Syntology ran 7 of 21 samples · 14 unverified · 6 pointer-only (licence)
  We consider the two related problems of detecting if an example is misclassified or out-of-distribution.
• Deep Anomaly Detection with Outlier Exposure
  11 Dec 2018 9 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 4 pointer-only (licence)
  We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.
• Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
  8 Jun 2017 9 repositories listed Syntology ran 2 of 3 samples · 1 unverified · 1 pointer-only (licence)
  We show in a series of experiments that ODIN is compatible with diverse network architectures and datasets.
• Energy-based Out-of-distribution Detection
  8 Oct 2020 6 repositories listed Syntology ran 3 of 6 samples · 3 unverified
  We propose a unified framework for OOD detection that uses an energy score.
• MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space
  5 May 2021 5 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 1 pointer-only (licence)
  Detecting out-of-distribution (OOD) inputs is a central challenge for safely deploying machine learning models in the real world.
• Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
  28 Dec 2019 5 repositories listed Syntology ran 5 of 8 samples · 3 unverified · 8 pointer-only (licence)
  We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates.
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
  13 Feb 2018 5 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong.
• GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection
  10 Apr 2023 4 repositories listed Syntology ran 5 of 16 samples · 11 unverified
  Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names.
• OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
  13 Oct 2022 4 repositories listed Syntology ran 8 of 17 samples · 9 unverified
  Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature.
• Generalized Out-of-Distribution Detection: A Survey
  21 Oct 2021 4 repositories listed
  In this survey, we first present a unified framework called generalized OOD detection, which encompasses the five aforementioned problems, i.
• A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
  15 Jul 2021 4 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  Conformal prediction is a user-friendly paradigm for creating statistically rigorous uncertainty sets/intervals for the predictions of such models.
• Open-set Label Noise Can Improve Robustness Against Inherent Label Noise
  21 Jun 2021 4 repositories listed Syntology ran 17 of 29 samples · 12 unverified · 29 pointer-only (licence)
  Learning with noisy labels is a practically challenging problem in weakly supervised learning.
• A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
  16 Jun 2021 4 repositories listed
  Mahalanobis distance (MD) is a simple and popular post-processing method for detecting out-of-distribution (OOD) inputs in neural networks.
• Hierarchical VAEs Know What They Don't Know
  16 Feb 2021 4 repositories listed Syntology ran 8 of 10 samples · 2 unverified · 9 pointer-only (licence)
  Deep generative models have been demonstrated as state-of-the-art density estimators.
• Masksembles for Uncertainty Estimation
  15 Dec 2020 4 repositories listed
  Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples.
• Probabilistic Autoencoder
  9 Jun 2020 4 repositories listed Syntology ran 1 of 13 samples · 12 unverified
  The PAE is fast and easy to train and achieves small reconstruction errors, high sample quality, and good performance in downstream tasks.
• Scaling Out-of-Distribution Detection for Real-World Settings
  25 Nov 2019 4 repositories listed Syntology ran 3 of 4 samples · 1 unverified
  We conduct extensive experiments in these more realistic settings for out-of-distribution detection and find that a surprisingly simple detector based on the maximum logit outperforms prior methods in all the…
• Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
  28 Jun 2019 4 repositories listed Syntology ran 5 of 12 samples · 7 unverified
  Self-supervision provides effective representations for downstream tasks without requiring labels.
• Likelihood Ratios for Out-of-Distribution Detection
  7 Jun 2019 4 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
  10 Jul 2018 4 repositories listed Syntology ran 9 of 13 samples · 4 unverified · 12 pointer-only (licence)
  Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning…
• Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-wise Regression
  14 Aug 2023 3 repositories listed
  For that purpose, we adapted the U-Net architecture to train multiple subnetworks within a single model, harnessing the overparameterization in deep neural networks.
• OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection
  15 Jun 2023 3 repositories listed
  Out-of-Distribution (OOD) detection is critical for the reliable operation of open-world intelligent systems.
• GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models
  5 Oct 2022 3 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Going beyond this, we propose GMMSeg, a new family of segmentation models that rely on a dense generative classifier for the joint distribution p(pixel feature, class).
• Out of Distribution Detection via Neural Network Anchoring
  8 Jul 2022 3 repositories listed
  Our goal in this paper is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection.
• Out-of-Distribution Detection with Deep Nearest Neighbors
  13 Apr 2022 3 repositories listed Syntology ran 30 of 38 samples · 8 unverified · 38 pointer-only (licence)
  In this paper, we explore the efficacy of non-parametric nearest-neighbor distance for OOD detection, which has been largely overlooked in the literature.
• Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization
  30 Sep 2021 3 repositories listed Syntology ran 2 of 8 samples · 6 unverified
  We introduce a simple and intuitive self-supervision task, Natural Synthetic Anomalies (NSA), for training an end-to-end model for anomaly detection and localization using only normal training data.
• SSD: A Unified Framework for Self-Supervised Outlier Detection
  22 Mar 2021 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  We demonstrate that SSD outperforms most existing detectors based on unlabeled data by a large margin.
• A Benchmark of Medical Out of Distribution Detection
  8 Jul 2020 3 repositories listed Syntology ran 2 of 7 samples · 5 unverified
  However it is unclear which OoDD method should be used in practice.
• Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
  17 Jan 2020 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of {\em controlled} information…

Syntology lines on 24 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.