Towards Combined Open Set Recognition and Out-of-Distribution Detection for Fine-grained Classification

Alexander Gillert, Uwe Freiherr von Lukas, Uwe Freiherr von Lukas

2021

Abstract

We analyze the two very similar problems of Out-of-Distribution (OOD) Detection and Open Set Recognition (OSR) in the context of fine-grained classification. Both problems are about detecting object classes that a classifier was not trained on, but while the former aims to reject invalid inputs, the latter aims to detect valid but unknown classes. Previous works on OOD detection and OSR methods are evaluated mostly on very simple datasets or datasets with large inter-class variance and perform poorly in the fine-grained setting. In our experiments, we show that object detection works well to recognize invalid inputs and techniques from the field of fine-grained classification, like individual part detection or zooming into discriminative local regions, are helpful for fine-grained OSR.

Paper Citation

in Harvard Style

Gillert A. and von Lukas U. (2021). Towards Combined Open Set Recognition and Out-of-Distribution Detection for Fine-grained Classification. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 225-233. DOI: 10.5220/0010340702250233

in Bibtex Style

@conference{visapp21,
author={Alexander Gillert and Uwe Freiherr von Lukas},
title={Towards Combined Open Set Recognition and Out-of-Distribution Detection for Fine-grained Classification},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={225-233},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010340702250233},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Towards Combined Open Set Recognition and Out-of-Distribution Detection for Fine-grained Classification
SN - 978-989-758-488-6
AU - Gillert A.
AU - von Lukas U.
PY - 2021
SP - 225
EP - 233
DO - 10.5220/0010340702250233
PB - SciTePress