Calibrated Out-of-Distribution Detection with a Generic Representation

Result code in 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>

Result on the web

<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>

Result language

angličtina

Original language name

Calibrated Out-of-Distribution Detection with a Generic Representation

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Publication year

2023

Confidentiality

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

Article name in the collection

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

ISBN

979-8-3503-0744-3

ISSN

2473-9936

e-ISSN

2473-9944

Number of pages

10

Pages from-to

4509-4518

Publisher name

IEEE

Place of publication

Anchorage, Alaska

Event location

Paris

Event date

Oct 2, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001156680304064