Calibrated Out-of-Distribution Detection with a Generic Representation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00371043" target="_blank" >RIV/68407700:21230/23:00371043 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCVW60793.2023.00485" target="_blank" >https://doi.org/10.1109/ICCVW60793.2023.00485</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCVW60793.2023.00485" target="_blank" >10.1109/ICCVW60793.2023.00485</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Calibrated Out-of-Distribution Detection with a Generic Representation

Popis výsledku v původním jazyce

Out-of-distribution detection is a common issue in deploying vision models in practice and solving it is an essential building block in safety critical applications. Most of the existing OOD detection solutions focus on improving the OOD robustness of a classification model trained exclusively on in-distribution (ID) data. In this work, we take a different approach and propose to leverage generic pre-trained representation. We propose a novel OOD method, called GROOD, that formulates the OOD detection as a Neyman-Pearson task with well calibrated scores and which achieves excellent performance, predicated by the use of a good generic representation. Only a trivial training process is required for adapting GROOD to a particular problem. The method is simple, general, efficient, calibrated and with only a few hyper-parameters. The method achieves state-of-the-art performance on a number of OOD benchmarks, reaching near perfect performance on several of them. The source code is available at https://github.com/vojirt/GROOD.

Název v anglickém jazyce

Calibrated Out-of-Distribution Detection with a Generic Representation

Popis výsledku anglicky

Out-of-distribution detection is a common issue in deploying vision models in practice and solving it is an essential building block in safety critical applications. Most of the existing OOD detection solutions focus on improving the OOD robustness of a classification model trained exclusively on in-distribution (ID) data. In this work, we take a different approach and propose to leverage generic pre-trained representation. We propose a novel OOD method, called GROOD, that formulates the OOD detection as a Neyman-Pearson task with well calibrated scores and which achieves excellent performance, predicated by the use of a good generic representation. Only a trivial training process is required for adapting GROOD to a particular problem. The method is simple, general, efficient, calibrated and with only a few hyper-parameters. The method achieves state-of-the-art performance on a number of OOD benchmarks, reaching near perfect performance on several of them. The source code is available at https://github.com/vojirt/GROOD.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

ICCVW2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

ISBN

979-8-3503-0744-3

ISSN

2473-9936

e-ISSN

2473-9944

Počet stran výsledku

10

Strana od-do

4509-4518

Název nakladatele

IEEE

Místo vydání

Anchorage, Alaska

Místo konání akce

Paris

Datum konání akce

2. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001156680304064