Deep compact polyhedral conic classifier for open and closed set recognition

Hakan Çevıkalp

doi:10.1016/j.patcog.2021.108080

Deep compact polyhedral conic classifier for open and closed set recognition

2021-11-01

15

OA

AI

DOI：10.1016/j.patcog.2021.108080

Original

Save

View PDF

Abstract

En 中文

In this paper, we propose a new deep neural network classifier that simultaneously maximizes the interclass separation and minimizes the intra-class variation by using the polyhedral conic classification function. The proposed method has one loss term that allows the margin maximization to maximize the interclass separation and another loss term that controls the compactness of the class acceptance regions. Our proposed method has a nice geometric interpretation using polyhedral conic function geometry. We tested the proposed method on various visual classification problems including closed/open set recognition and anomaly detection. The experimental results show that the proposed method typically outperforms other state-of-the-art methods, and becomes a better choice compared to other tested methods especially for open set recognition type problems. The source code of the proposed method is available at https://github.com/bdrhn9/dc-epcc . (c) 2021 Elsevier Ltd. All rights reserved.

Keywords:

Polyhedral conic classifier

Deep learning

Open set recognition

Image classification

Anomaly detection

Deep compact polyhedral conic classifier for open and closed set recognition

Abstract

AI Summary

Journal

Organization