PyTorch Out-of-Distribution Detection

A Python library for Out-of-Distribution (OOD) Detection with Deep Neural Networks based on PyTorch.

The library provides:

• Out-of-Distribution Detection Methods
• Loss Functions
• Datasets
• Neural Network Architectures, as well as pre-trained weights
• Data Augmentations
• Useful Utilities

and is designed to be compatible with frameworks like pytorch-lightning and pytorch-segmentation-models. The library also covers some methods from closely related fields, such as Open-Set Recognition, Novelty Detection, Confidence Estimation and Anomaly Detection.

📚 Documentation

The documentation is available here.

NOTE: An important convention adopted in pytorch-ood is that OOD detectors predict outlier scores that should be larger for outliers than for inliers. If you notice that the scores predicted by a detector do not match the formulas in the corresponding publication, we may have adjusted the score calculation to comply with this convention.

⏳ Quick Start

Load a WideResNet-40 model (used in major publications), pre-trained on CIFAR-10 with the Energy-Bounded Learning Loss [8] (weights from to original paper), and predict on some dataset data_loader using Energy-based OOD Detection (EBO) [8], calculating the common metrics. OOD data must be marked with labels < 0.

from pytorch_ood.detector import EnergyBased
from pytorch_ood.utils import OODMetrics
from pytorch_ood.model import WideResNet

data_loader = ... # your data, OOD with label < 0

# Create Neural Network
model = WideResNet(num_classes=10, pretrained="er-cifar10-tune").eval().cuda()
preprocess = WideResNet.transform_for("er-cifar10-tune")

# Create detector
detector = EnergyBased(model)

# Evaluate
metrics = OODMetrics()

for x, y in data_loader:
    x = preprocess(x).cuda()
    metrics.update(detector(x), y)

print(metrics.compute())

You can find more examples in the documentation.

Benchmarks (Beta)

Evaluate detectors against common benchmarks, for example the OpenOOD v1.5 CIFAR benchmark. All datasets will be downloaded automatically. When evaluating several detectors on the same benchmark, cached logits and pooled features can be reused across calls:

import pandas as pd
from pytorch_ood.benchmark import CIFAR10_OpenOOD
from pytorch_ood.detector import EnergyBased, MaxSoftmax
from pytorch_ood.model import WideResNet

model = WideResNet(num_classes=10, pretrained="cifar10-pt").eval().to("cuda:0")
trans = WideResNet.transform_for("cifar10-pt")

benchmark = CIFAR10_OpenOOD(root="data", transform=trans)
detectors = {
    "MSP": MaxSoftmax(model),
    "Energy": EnergyBased(model),
}

results = []
for name, detector in detectors.items():
    res = benchmark.evaluate(
        detector,
        loader_kwargs={"batch_size": 128, "num_workers": 12},
        device="cuda:0",
        cache=True,
        cache_dir="data/benchmark-cache",
        cache_key="cifar10-openood-wrn-cifar10-pt",
    )
    for row in res:
        row.update({"Detector": name})
    results += res

print(pd.DataFrame(results))

🛠 ️️Installation

The package can be installed via PyPI:

pip install pytorch-ood

Dependencies

• torch
• torchvision
• scipy
• torchmetrics

Optional Dependencies

• scikit-learn for ViM and k-NN
• gdown to download some datasets and model weights
• pandas for the examples.
• segmentation-models-pytorch to run the examples for anomaly segmentation

📝 Citing

If you use this project, please cite:

@inproceedings{kirchheim2022pytorch,
  title={Pytorch-ood: A library for out-of-distribution detection based on pytorch},
  author={Kirchheim, Konstantin and Filax, Marco and Ortmeier, Frank},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={4351--4360},
  year={2022}
}

📦 Implemented

Detectors:

Objective Functions:

Objective Function	Description	Year	Ref
Objectosphere	Implementation of the paper Reducing Network Agnostophobia.	2016	[9]
Center Loss	Generalized version of the Center Loss from the Paper A Discriminative Feature Learning Approach for Deep Face Recognition.	2016	[14]
Outlier Exposure	Implementation of the paper Deep Anomaly Detection With Outlier Exposure.	2018	[10]
Confidence Loss	Model learn confidence additional to class membership prediction.	2018	[7]
Deep SVDD	Implementation of the Deep Support Vector Data Description from the paper Deep One-Class Classification.	2018	[11]
Energy-Bounded Loss	Adds a regularization term to the cross-entropy that aims to increase the energy gap between IN and OOD samples.	2020	[8]
CAC Loss	Class Anchor Clustering Loss from Class Anchor Clustering: a Distance-based Loss for Training Open Set Classifiers	2021	[13]
Entropic Open-Set Loss	Entropy maximization and meta classification for OOD in semantic segmentation	2021	[40]
II Loss	Implementation of II Loss function from Learning a neural network-based representation for open set recognition.	2022	[12]
MCHAD Loss	Implementation of the MCHAD Loss from the paper Multi Class Hypersphere Anomaly Detection.	2022	[35]
VOS Energy-Based Loss	Implementation of the paper VOS: Learning what you don’t know by virtual outlier synthesis.	2022	[37]
Logit Normalization	Implementation of the paper Mitigating Neural Network Overconfidence with Logit Normalization.	2022	[46]

Image Datasets:

Dataset	Description	Year	Ref
Chars74k	The Chars74K dataset contains 74,000 images across 64 classes, comprising English letters and Arabic numerals.	2012	[31]
TinyImages	The TinyImages dataset is often used as auxiliary OOD training data. However, use is discouraged.	2012	[30]
Textures	Textures dataset, also known as DTD, often used as OOD Examples.	2013	[29]
FoolingImages	OOD Images Generated to fool certain Deep Neural Networks.	2015	[16]
Tiny ImageNet	A derived version of ImageNet with 64x64-sized images.	2015	[17]
TinyImages300k	A cleaned version of the TinyImages Dataset with 300.000 images, often used as auxiliary OOD training data.	2018	[10]
LSUN	A version of the Large-scale Scene UNderstanding Dataset with 10.000 images, often used as auxiliary OOD training data.	2018	[2]
MNIST-C	Corrupted version of the MNIST.	2019	[21]
CIFAR10-C	Corrupted version of the CIFAR 10.	2019	[15]
CIFAR100-C	Corrupted version of the CIFAR 100.	2019	[15]
ImageNet-C	Corrupted version of the ImageNet.	2019	[15]
ImageNet - A, O, R	Different Outlier Variants for the ImageNet.	2019	[18]
ImageNet - V2	A new test set for the ImageNet.	2019	[19]
ImageNet - ES	Event stream (ES) version of the ImageNet.	2021	[20]
iNaturalist	A Subset of iNaturalist, with 10.000 images.	2021	[34]
Fractals	A dataset with Fractals from PIXMIX: Dreamlike Pictures Comprehensively Improve Safety Measures	2022	[39]
Feature Visualizations	A dataset with Feature visualizations from PIXMIX: Dreamlike Pictures Comprehensively Improve Safety Measures	2022	[39]
FS Static	The FishyScapes (FS) Static dataset contains real world OOD images from the CityScapes dataset.	2021	[22]
FS LostAndFound	The FishyScapes dataset contains images from the CityScapes dataset blended with unknown objects scraped from the web.	2021	[22]
MVTech-AD	The MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection.	2021	[23]
StreetHazards	Anomaly Segmentation Dataset	2022	[24]
CIFAR100-GAN	Images sampled from low likelihood regions of a BigGAN trained on CIFAR 100 from the paper On Outlier Exposure with Generative Models.	2022	[25]
SSB - hard	The hard split of the Semantic Shift Benchmark, which contains 49.00 images.	2022	[26]
NINCO	The NINCO (No ImageNet Class Objects) dataset which contains 5.879 images of 64 OOD classes.	2023	[27]
SuMNIST	The SuMNIST dataset is based on MNIST but each image display four numbers instead of one.	2023	[28]
Gaussian Noise	Dataset with samples drawn from a normal distribution.
Uniform Noise	Dataset with samples drawn from a uniform distribution.

Text Datasets:

Dataset	Description	Year	Ref
Multi30k	Multi-30k dataset, as used by Hendrycks et al. in the OOD baseline paper.	2016	[32]
WikiText2	Texts from the wikipedia often used as auxiliary OOD training data.	2016	[33]
WikiText103	Texts from the wikipedia often used as auxiliary OOD training data.	2016	[33]
NewsGroup20	Texts from different newsgroups, as used by Hendrycks et al. in the OOD baseline paper.

Augmentation Methods:

Augmentation	Description	Year	Ref
PixMix	PixMix image augmentation method	2022	[39]
COCO Outlier Pasting	From "Entropy maximization and meta classification for OOD in semantic segmentation"	2021	[40]

Benchmarks:

Benchmark	Description	Year	Ref
CIFAR-10 ODIN	ODIN benchmark for CIFAR-10 OOD detection evaluation.	2018	[2]
CIFAR-10 OpenOOD	CIFAR-10 benchmark with OpenOOD protocol for standardized OOD evaluation.	2023	[59]
CIFAR-100 ODIN	ODIN benchmark for CIFAR-100 OOD detection evaluation.	2018	[2]
CIFAR-100 OpenOOD	CIFAR-100 benchmark with OpenOOD protocol for standardized OOD evaluation.	2023	[59]
ImageNet OpenOOD	ImageNet-1K OOD detection benchmark with OpenOOD protocol and evaluation suite.	2023	[59]
MIDOG OpenMIBOOD	Microscopy / mitosis detection with 4-way split (ID, covariate-shifted, near-OOD, far-OOD).	2025	[60]
PhaKIR OpenMIBOOD	Surgical video frames with 4-way split (ID, covariate-shifted, near-OOD, far-OOD).	2025	[60]
OASIS-3 OpenMIBOOD	Brain MRI volumes with 4-way split (ID, covariate-shifted, near-OOD, far-OOD).	2025	[60]

🤝 Contributing

We encourage everyone to contribute to this project by adding implementations of OOD Detection methods, datasets etc, or check the existing implementations for bugs.

🛡️ ️License

The code is licensed under Apache 2.0. We have taken care to make sure any third party code included or adapted has compatible (permissive) licenses such as MIT, BSD, etc. The legal implications of using pre-trained models in commercial services are, to our knowledge, not fully understood.

---

🔗 References

[1]	Bendale, A., & Boult, T. E. (2016). Towards open set deep networks. CVPR.

[2]	(1, 2, 3) Liang, S., et al. (2017). Enhancing the reliability of out-of-distribution image detection in neural networks. ICLR.

[3]	Lee, K., et al. (2018). A simple unified framework for detecting out-of-distribution samples and adversarial attacks. NeurIPS.

[4]	Gal, Y., & Ghahramani, Z. (2016). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. ICML.

[5]	Hendrycks, D., & Gimpel, K. (2016). A baseline for detecting misclassified and out-of-distribution examples in neural networks. ICLR.

[6]	Guo, C., et al. (2017). On calibration of modern neural networks. ICML.

[7]	DeVries, T., & Taylor, G. W. (2018). Learning confidence for out-of-distribution detection in neural networks. ArXiv.

[8]	(1, 2, 3) Liu, W., et al. (2020). Energy-based out-of-distribution detection. NeurIPS.

[9]	Dhamija, A. R., et al. (2018). Reducing network agnostophobia. NeurIPS.

[10]	(1, 2) Hendrycks, D., Mazeika, M., & Dietterich, T. (2018). Deep anomaly detection with outlier exposure. ICLR.

[11]	Ruff, L., et al. (2018). Deep one-class classification. ICML.

[12]	Hassen, M., & Chan, P. K. (2020). Learning a neural-network-based representation for open set recognition. SDM.

[13]	Miller, D., et al. (2021). Class anchor clustering: A loss for distance-based open set recognition. WACV.

[14]	Wen, Y., et al. (2016). A discriminative feature learning approach for deep face recognition. ECCV.

[15]	(1, 2, 3) Hendrycks, D., & Dietterich, T. (2019). Benchmarking neural network robustness to common corruptions and perturbations. ICLR.

[16]	Nguyen, A., et al. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. CVPR.

[17]	Le, Y., et al. (2015). Tiny ImageNet Visual Recognition Challenge. Stanford.

[18]	Hendrycks, D., et al. (2021). Natural adversarial examples. CVPR.

[19]	Recht, B., et al. (2019). Do imagenet classifiers generalize to imagenet?. PMLR.

[20]	Lin, Y., et al. (2021). ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks. Front Neurosci.

[21]	Mu, N., & Gilmer, J. (2019). MNIST-C: A robustness benchmark for computer vision. ICLR Workshop.

[22]	(1, 2) Blum, H. et al (2021) The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation. IJCV.

[23]	Bergmann, P. et al (2021) The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection. IJCV

[24]	Hendrycks, D., et al. (2022). Scaling out-of-distribution detection for real-world settings. ICML.

[25]	Kirchheim, K., & Ortmeier, F. (2022) On Outlier Exposure with Generative Models. NeurIPS.

[26]	Vaze, S., et al. (2022) Open-set recognition: A good closed-set classifier is all you need. ICLR.

[27]	Bitterwolf, J., et al. (2023) In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation. ICML.

[28]	Kirchheim, K. (2023) Towards Deep Anomaly Detection with Structured Knowledge Representations. SAFECOMP.

[29]	Cimpoi, M., et al. (2014). Describing textures in the wild. CVPR.

[30]	Torralba, A., et al. (2007). 80 million tiny images: a large dataset for non-parametric object and scene recognition. IEEE Transactions on Pattern Analysis and Machine Learning.

[31]	de Campos, T. E., et al. (2009). Character recognition in natural images. In Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP).

[32]	Elliott, D., et al. (2016). Multi30k: Multilingual english-german image descriptions. Proceedings of the 5th Workshop on Vision and Language.

[33]	(1, 2) Merity, S., et al. (2016). Pointer sentinel mixture models. ArXiv

[34]	Huang, R., & Li, Y. (2021) MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space. CVPR.

[35]	Kirchheim, K., et al. (2022) Multi Class Hypersphere Anomaly Detection. ICPR.

[36]	Wang, H., et al. (2022) ViM: Out-Of-Distribution with Virtual-logit Matching. CVPR.

[37]	Du, X., et al. (2022) VOS: Learning What You Don't Know by Virtual Outlier Synthesis. ICLR.

[38]	Sun, Y., et al. (2022) Out-of-Distribution Detection with Deep Nearest Neighbors. ICML.

[39]	(1, 2, 3) Hendrycks, D, et al. (2022) PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures. CVPR.

[40]	(1, 2) Chan R, et al. (2021) Entropy maximization and meta classification for out-of-distribution detection in semantic segmentation. CVPR.

[41]	Sun, et al. (2022) DICE: Leveraging Sparsification for Out-of-Distribution Detection. ECCV.

[42]	Djurisic, et al. (2023) Extremely Simple Activation Shaping for Out-of-Distribution Detection, ICLR.

[43]	Zhang, et al. (2023) Out-of-Distribution Detection Based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy. ICLR.

[44]	Sun, et al. (2023) ReAct: Out-of-distribution Detection With Rectified Activations. NeurIPS.

[45]	Shama, et al. (2019) Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices. NeurIPS.

[46]	Wei, et al. (2022) Mitigating Neural Network Overconfidence with Logit Normalization. ICML.

[47]	Liu, et al. (2025) Detecting Out-of-distribution through the Lens of Neural Collapse. CVPR.

[48]	Park, J., et al. (2023) Nearest Neighbor Guidance for Out-of-Distribution Detection. ICCV.

[49]	Lee, J., & AlRegib, G. (2020) Gradients as a Measure of Uncertainty in Neural Networks. ICIP.

[50]	Huang, R., et al. (2021) On the Importance of Gradients for Detecting Distributional Shifts in the Wild. NeurIPS.

[51]	Ren, J., et al. (2021) A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection. ArXiv.

[52]	Song, Y., et al. (2022) Rankfeat: Rank-1 Feature Removal for Out-of-Distribution Detection. NeurIPS.

[53]	Liu, X., et al. (2023) GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection. CVPR.

[54]	Liu, L., & Qin, Y. (2023) Fast Decision Boundary based Out-of-Distribution Detector. ArXiv.

[55]	Bibas, K., Feder, M., & Hassner, T. (2021) Single Layer Predictive Normalized Maximum Likelihood for Out-of-Distribution Detection. ArXiv.

[56]	Xu, M., et al. (2023) VRA: Variational Rectified Activation for Out-of-Distribution Detection. ArXiv.

[57]	Liu, Y., et al. (2023) Neuron Activation Coverage: Rethinking Out-of-Distribution Detection and Generalization. ICLR.

[58]	Ming, Y., Cai, Z., Gu, J., Sun, Y., Li, W., & Li, Y. (2022) Delving into Out-of-Distribution Detection with Vision-Language Representations. NeurIPS. ArXiv.

[59]	(1, 2, 3) Zhang, J., Yang, J., et al. (2023) OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection. DMLR. ArXiv.

[60]	(1, 2, 3) Gutbrod, M., Rauber, D., Nunes, D. W., & Palm, C. (2025) OpenMIBOOD: Open Medical Imaging Benchmarks for Out-Of-Distribution Detection. CVPR. ArXiv.