Generative OpenMax for Multi-Class Open Set Classification

TL;DR

This paper introduces Generative OpenMax, a novel method for multi-class open set classification that uses GANs to explicitly model and identify unknown classes, improving detection and visualization of novel categories.

Contribution

It extends OpenMax by integrating GANs for synthesizing unknown class images, enabling explicit modeling and better detection of unknown classes.

Findings

G-OpenMax outperforms previous methods on handwritten digit and character datasets.

It provides visualizations of unknown class samples from open space.

The approach demonstrates improved open set classification accuracy.

Abstract

We present a conceptually new and flexible method for multi-class open set classification. Unlike previous methods where unknown classes are inferred with respect to the feature or decision distance to the known classes, our approach is able to provide explicit modelling and decision score for unknown classes. The proposed method, called Gener- ative OpenMax (G-OpenMax), extends OpenMax by employing generative adversarial networks (GANs) for novel category image synthesis. We validate the proposed method on two datasets of handwritten digits and characters, resulting in superior results over previous deep learning based method OpenMax Moreover, G-OpenMax provides a way to visualize samples representing the unknown classes from open space. Our simple and effective approach could serve as a new direction to tackle the challenging multi-class open set classification problem.