Single and Combined Algorithms for Open Set Classification on Image Datasets

Modafar Al-Shouha; Gábor Szűcs

doi:10.14232/actacyb.298356

Modafar Al-Shouha Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary https://orcid.org/0000-0003-2051-4036
Gábor Szűcs Department of Telecommunications and Media Informatics, Budapest University of Technology and Economics, Hungary https://orcid.org/0000-0002-5781-1088

DOI: https://doi.org/10.14232/actacyb.298356

Keywords: binary classification, multi-class classification, GAN, out-of-distribution, open set classification

Abstract

Generally, classification models have closed nature, and they are constrained by the number of classes in the training data. Hence, classifying "unknown" - OOD (out-of-distribution) - samples is challenging, especially in the so called "open set" problem. We propose and investigate different solutions - single and combined algorithms - to tackle this task, where we use and expand a K-classifier to be able to identify K+1 classes. They do not require any retraining or modification on the K-classifier architecture. We show their strengths when avoiding type I or type II errors is fundamental. We also present a mathematical representation for the task to estimate the K+1 classification accuracy, and an inequality that defines its boundaries. Additionally, we introduce a formula to calculate the exact K+1 classification accuracy.

Downloads

Download data is not yet available.