# A framework for benchmarking class-out-of-distribution detection and its application to ImageNet

arXiv: https://arxiv.org/abs/2302.11893 · HTML: https://mlsanity.com/paper/2302.11893/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 23 Feb 2023.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [Exploring the Limits of Out-of-Distribution Detection](https://mlsanity.com/paper/2106.03004/) (2021)
- [When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations](https://mlsanity.com/paper/2106.01548/) (2021)
- [Billion-scale semi-supervised learning for image classification](https://mlsanity.com/paper/1905.00546/) (2019)
- [Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP](https://mlsanity.com/paper/2109.02748/) (2021)
- [Revisiting Weakly Supervised Pre-Training of Visual Perception Models](https://mlsanity.com/paper/2201.08371/) (2022)
- [Confidence-based Out-of-Distribution Detection: A Comparative Study and Analysis](https://mlsanity.com/paper/2107.02568/) (2021)
- [Out-of-Distribution Detection using Multiple Semantic Label Representations](https://mlsanity.com/paper/1808.06664/) (2018)

## Built on by (most cited first, 30 of 31)

- [OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection](https://mlsanity.com/paper/2306.09301/) (2023)
- [In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation](https://mlsanity.com/paper/2306.00826/) (2023)
- [Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks](https://mlsanity.com/paper/2402.19460/) (2024)
- [Dream the Impossible: Outlier Imagination with Diffusion Models](https://mlsanity.com/paper/2309.13415/) (2023)
- [How Does Unlabeled Data Provably Help Out-of-Distribution Detection?](https://mlsanity.com/paper/2402.03502/) (2024)
- [Mahalanobis++: Improving OOD Detection via Feature Normalization](https://mlsanity.com/paper/2505.18032/) (2025)
- [ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms](https://mlsanity.com/paper/2310.01755/) (2023)
- [URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates](https://mlsanity.com/paper/2307.03810/) (2023)
- [A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?](https://mlsanity.com/paper/2404.01775/) (2024)
- [Pretrained Visual Uncertainties](https://mlsanity.com/paper/2402.16569/) (2024)
- [No Free Lunch: The Hazards of Over-Expressive Representations in Anomaly Detection](https://mlsanity.com/paper/2306.07284/) (2023)
- [When and How Does In-Distribution Label Help Out-of-Distribution Detection?](https://mlsanity.com/paper/2405.18635/) (2024)
- [Building Machine Learning Challenges for Anomaly Detection in Science](https://mlsanity.com/paper/2503.02112/) (2025)
- [Out-of-Distribution Detection using Synthetic Data Generation](https://mlsanity.com/paper/2502.03323/) (2025)
- [Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox](https://mlsanity.com/paper/2406.09867/) (2024)
- [Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring](https://mlsanity.com/paper/2503.01691/) (2025)
- [How to train your ViT for OOD Detection](https://mlsanity.com/paper/2405.17447/) (2024)
- [Out-of-Distribution Detection with Relative Angles](https://mlsanity.com/paper/2410.04525/) (2024)
- [Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impact](https://mlsanity.com/paper/2412.19124/) (2024)
- [Medix: Out-of-Distribution Detection from Unlabeled Wild Data via Robust Gradient Statistics](https://mlsanity.com/paper/2510.06505/) (2025)
- [Uncertainties of Latent Representations in Computer Vision](https://mlsanity.com/paper/2408.14281/) (2024)
- [Integrating uncertainty quantification into randomized smoothing based robustness guarantees](https://mlsanity.com/paper/2410.20432/) (2024)
- [Legitimate ground-truth-free metrics for deep uncertainty classification scoring](https://mlsanity.com/paper/2410.23046/) (2024)
- [BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2411.13251/) (2024)
- [One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection](https://mlsanity.com/paper/2601.10836/) (2026)
- [Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection](https://mlsanity.com/paper/2303.05828/) (2023)
- [Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detection](https://mlsanity.com/paper/2409.03801/) (2024)
- [Control+Shift: Generating Controllable Distribution Shifts](https://mlsanity.com/paper/2409.07940/) (2024)
- [COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP](https://mlsanity.com/paper/2507.22576/) (2025)
- [ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora](https://mlsanity.com/paper/2511.07068/) (2025)

## Abstract (arXiv)

When deployed for risk-sensitive tasks, deep neural networks must be able to detect instances with labels from outside the distribution for which they were trained. In this paper we present a novel framework to benchmark the ability of image classifiers to detect class-out-of-distribution instances (i.e., instances whose true labels do not appear in the training distribution) at various levels of detection difficulty. We apply this technique to ImageNet, and benchmark 525 pretrained, publicly available, ImageNet-1k classifiers. The code for generating a benchmark for any ImageNet-1k classifier, along with the benchmarks prepared for the above-mentioned 525 models is available at https://github.com/mdabbah/COOD_benchmarking. The usefulness of the proposed framework and its advantage over alternative existing benchmarks is demonstrated by analyzing the results obtained for these models, which reveals numerous novel observations including: (1) knowledge distillation consistently improves class-out-of-distribution (C-OOD) detection performance; (2) a subset of ViTs performs better C-OOD detection than any other model; (3) the language--vision CLIP model achieves good zero-shot detection performance, with its best instance outperforming 96% of all other models evaluated; (4) accuracy and in-distribution ranking are positively correlated to C-OOD detection; and (5) we compare various confidence functions for C-OOD detection. Our companion paper, also published in ICLR 2023 (What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers), examines the uncertainty estimation performance (ranking, calibration, and selective prediction performance) of these classifiers in an in-distribution setting.