Unseen Class Discovery in Open-world Classification

TL;DR

This paper addresses open-world classification by proposing a model that not only classifies seen classes but also discovers unseen classes among rejected examples using a similarity-based clustering approach.

Contribution

It introduces a joint classification model with a sub-model for pairwise class similarity, enabling discovery of hidden unseen classes in rejected examples.

Findings

Model effectively classifies seen classes.

Sub-model accurately measures pairwise similarity.

Clustering reveals hidden unseen classes.

Abstract

This paper concerns open-world classification, where the classifier not only needs to classify test examples into seen classes that have appeared in training but also reject examples from unseen or novel classes that have not appeared in training. Specifically, this paper focuses on discovering the hidden unseen classes of the rejected examples. Clearly, without prior knowledge this is difficult. However, we do have the data from the seen training classes, which can tell us what kind of similarity/difference is expected for examples from the same class or from different classes. It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them. This paper aims to solve this problem. It first proposes a joint open classification model with a sub-model for classifying whether a pair of examples belongs to the same or different classes. This sub-model can serve as a distance function for clustering to discover the hidden classes of the rejected examples. Experimental results show that the proposed model is highly promising.