Adaptive Out-of-Distribution Detection with Coarse-to-Fine Grained Representation

Kohei Fukuda, Hiroaki Aizawa

2025

Abstract

Out-of-distribution (OOD) detection, which aims to identify data sampled from a distribution different from the training data, is crucial for practical machine learning applications. Despite the coarse-to-fine structure of OOD data, which includes features at various granularities of detail, such as object shapes (coarse features) and textures (fine features), most existing methods represent an image as a fixed-length feature vector and perform detection by calculating a single OOD score from this vector. To consider the coarse-to-fine structure of OOD data, we propose a method for detecting OOD data that uses feature vectors that contain information at different granularities obtained by Matryoshka representation learning. Adaptive sub-feature vectors are selected for each OOD dataset. The OOD scores calculated from these vectors are taken as the final OOD scores. Experiments show that the proposed method outperforms existing methods in terms of OOD detection. Moreover, we analyze the relationship between each OOD dataset and the sub-feature vectors selected by our method.

Paper Citation

in Harvard Style

Fukuda K. and Aizawa H. (2025). Adaptive Out-of-Distribution Detection with Coarse-to-Fine Grained Representation. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 19-26. DOI: 10.5220/0013100100003912

in Bibtex Style

@conference{visapp25,
author={Kohei Fukuda and Hiroaki Aizawa},
title={Adaptive Out-of-Distribution Detection with Coarse-to-Fine Grained Representation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={19-26},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013100100003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Adaptive Out-of-Distribution Detection with Coarse-to-Fine Grained Representation
SN - 978-989-758-728-3
AU - Fukuda K.
AU - Aizawa H.
PY - 2025
SP - 19
EP - 26
DO - 10.5220/0013100100003912
PB - SciTePress