Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition

TL;DR

This paper introduces a deep neural network classifier using polyhedral conic functions that enhances class separation and compactness, improving performance in open and closed set recognition and anomaly detection tasks.

Contribution

The paper presents a novel deep classifier with a unique loss function based on polyhedral conic geometry, effectively handling open and closed set recognition challenges.

Findings

Outperforms state-of-the-art methods in various visual classification tasks.

Achieves superior results in open set recognition scenarios.

Provides a geometric interpretation of classification boundaries.

Abstract

In this paper, we propose a new deep neural network classifier that simultaneously maximizes the inter-class 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 inter-class 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.