PyTorch-OOD: A Library for Out-of-Distribution Detection based on PyTorch. Kirchheim, K., Filax, M., & Ortmeier, F. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2022-June:4350-4359, IEEE Computer Society, 2022. ![PyTorch-OOD: A Library for Out-of-Distribution Detection based on PyTorch [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex Machine Learning models based on Deep Neural Networks behave unpredictably when presented with inputs that do not stem from the training distribution and sometimes make egregiously wrong predictions with high confidence. This property undermines the trustworthiness of systems depending on such models and potentially threatens the safety of their users. Out-of-Distribution (OOD) detection mechanisms can be used to prevent errors by detecting inputs that are so dissimilar from the training set that the model can not be expected to make reliable predictions. In this paper, we present PyTorch-OOD, a Python library for OOD detection based on PyTorch. Its primary goals are to accelerate OOD detection research and improve the reproducibility and comparability of experiments. PyTorch-OOD provides well-tested and documented implementations of OOD detection methods with a unified interface, as well as training and benchmark datasets, architectures, pre-trained models, and utility functions. The library is available online 1 under the permissive Apache 2.0 license and can be installed via Python Package Index (PyPI).
@article{
title = {PyTorch-OOD: A Library for Out-of-Distribution Detection based on PyTorch},
type = {article},
year = {2022},
pages = {4350-4359},
volume = {2022-June},
publisher = {IEEE Computer Society},
id = {0ba55f41-685f-3f71-9d30-1dd32173a28a},
created = {2022-11-18T10:39:42.207Z},
accessed = {2022-11-18},
file_attached = {true},
profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2023-04-03T10:17:19.003Z},
read = {true},
starred = {false},
authored = {false},
confirmed = {false},
hidden = {false},
folder_uuids = {5a010301-acb6-4642-a6b2-8afaee1b741c,4b11b59b-846d-45b5-82b7-81d8bc3108b2,bd3c6f2e-3514-47cf-bc42-12db8b9abe45},
private_publication = {false},
abstract = {Machine Learning models based on Deep Neural Networks behave unpredictably when presented with inputs that do not stem from the training distribution and sometimes make egregiously wrong predictions with high confidence. This property undermines the trustworthiness of systems depending on such models and potentially threatens the safety of their users. Out-of-Distribution (OOD) detection mechanisms can be used to prevent errors by detecting inputs that are so dissimilar from the training set that the model can not be expected to make reliable predictions. In this paper, we present PyTorch-OOD, a Python library for OOD detection based on PyTorch. Its primary goals are to accelerate OOD detection research and improve the reproducibility and comparability of experiments. PyTorch-OOD provides well-tested and documented implementations of OOD detection methods with a unified interface, as well as training and benchmark datasets, architectures, pre-trained models, and utility functions. The library is available online 1 under the permissive Apache 2.0 license and can be installed via Python Package Index (PyPI).},
bibtype = {article},
author = {Kirchheim, Konstantin and Filax, Marco and Ortmeier, Frank},
doi = {10.1109/CVPRW56347.2022.00481},
journal = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops}
}
Downloads: 0
{"_id":"AdjWbJ5kMQgDMu82c","bibbaseid":"kirchheim-filax-ortmeier-pytorchoodalibraryforoutofdistributiondetectionbasedonpytorch-2022","author_short":["Kirchheim, K.","Filax, M.","Ortmeier, F."],"bibdata":{"title":"PyTorch-OOD: A Library for Out-of-Distribution Detection based on PyTorch","type":"article","year":"2022","pages":"4350-4359","volume":"2022-June","publisher":"IEEE Computer Society","id":"0ba55f41-685f-3f71-9d30-1dd32173a28a","created":"2022-11-18T10:39:42.207Z","accessed":"2022-11-18","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2023-04-03T10:17:19.003Z","read":"true","starred":false,"authored":false,"confirmed":false,"hidden":false,"folder_uuids":"5a010301-acb6-4642-a6b2-8afaee1b741c,4b11b59b-846d-45b5-82b7-81d8bc3108b2,bd3c6f2e-3514-47cf-bc42-12db8b9abe45","private_publication":false,"abstract":"Machine Learning models based on Deep Neural Networks behave unpredictably when presented with inputs that do not stem from the training distribution and sometimes make egregiously wrong predictions with high confidence. This property undermines the trustworthiness of systems depending on such models and potentially threatens the safety of their users. Out-of-Distribution (OOD) detection mechanisms can be used to prevent errors by detecting inputs that are so dissimilar from the training set that the model can not be expected to make reliable predictions. In this paper, we present PyTorch-OOD, a Python library for OOD detection based on PyTorch. Its primary goals are to accelerate OOD detection research and improve the reproducibility and comparability of experiments. PyTorch-OOD provides well-tested and documented implementations of OOD detection methods with a unified interface, as well as training and benchmark datasets, architectures, pre-trained models, and utility functions. The library is available online 1 under the permissive Apache 2.0 license and can be installed via Python Package Index (PyPI).","bibtype":"article","author":"Kirchheim, Konstantin and Filax, Marco and Ortmeier, Frank","doi":"10.1109/CVPRW56347.2022.00481","journal":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops","bibtex":"@article{\n title = {PyTorch-OOD: A Library for Out-of-Distribution Detection based on PyTorch},\n type = {article},\n year = {2022},\n pages = {4350-4359},\n volume = {2022-June},\n publisher = {IEEE Computer Society},\n id = {0ba55f41-685f-3f71-9d30-1dd32173a28a},\n created = {2022-11-18T10:39:42.207Z},\n accessed = {2022-11-18},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2023-04-03T10:17:19.003Z},\n read = {true},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n folder_uuids = {5a010301-acb6-4642-a6b2-8afaee1b741c,4b11b59b-846d-45b5-82b7-81d8bc3108b2,bd3c6f2e-3514-47cf-bc42-12db8b9abe45},\n private_publication = {false},\n abstract = {Machine Learning models based on Deep Neural Networks behave unpredictably when presented with inputs that do not stem from the training distribution and sometimes make egregiously wrong predictions with high confidence. This property undermines the trustworthiness of systems depending on such models and potentially threatens the safety of their users. Out-of-Distribution (OOD) detection mechanisms can be used to prevent errors by detecting inputs that are so dissimilar from the training set that the model can not be expected to make reliable predictions. In this paper, we present PyTorch-OOD, a Python library for OOD detection based on PyTorch. Its primary goals are to accelerate OOD detection research and improve the reproducibility and comparability of experiments. PyTorch-OOD provides well-tested and documented implementations of OOD detection methods with a unified interface, as well as training and benchmark datasets, architectures, pre-trained models, and utility functions. The library is available online 1 under the permissive Apache 2.0 license and can be installed via Python Package Index (PyPI).},\n bibtype = {article},\n author = {Kirchheim, Konstantin and Filax, Marco and Ortmeier, Frank},\n doi = {10.1109/CVPRW56347.2022.00481},\n journal = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops}\n}","author_short":["Kirchheim, K.","Filax, M.","Ortmeier, F."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/05aa1847-0580-bddb-2189-b05935dfbe1a/full_text.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"kirchheim-filax-ortmeier-pytorchoodalibraryforoutofdistributiondetectionbasedonpytorch-2022","role":"author","metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":[],"search_terms":["pytorch","ood","library","out","distribution","detection","based","pytorch","kirchheim","filax","ortmeier"],"title":"PyTorch-OOD: A Library for Out-of-Distribution Detection based on PyTorch","year":2022}