Spatial Location Constraint Prototype Loss for Open Set Recognition

TL;DR

This paper introduces a novel loss function called spatial location constraint prototype loss designed to improve open set recognition by effectively reducing both empirical and open space risks, demonstrated through extensive experiments.

Contribution

It proposes a new loss function that explicitly constrains class prototypes based on spatial location to enhance open set recognition performance.

Findings

Outperforms existing methods on multiple benchmarks

Effectively reduces open space risk and empirical risk

Provides clear visualization of feature distributions

Abstract

One of the challenges in pattern recognition is open set recognition. Compared with closed set recognition, open set recognition needs to reduce not only the empirical risk, but also the open space risk, and the reduction of these two risks corresponds to classifying the known classes and identifying the unknown classes respectively. How to reduce the open space risk is the key of open set recognition. This paper explores the origin of the open space risk by analyzing the distribution of known and unknown classes features. On this basis, the spatial location constraint prototype loss function is proposed to reduce the two risks simultaneously. Extensive experiments on multiple benchmark datasets and many visualization results indicate that our methods is superior to most existing approaches.