Open-Set Representation Learning through Combinatorial Embedding

TL;DR

This paper introduces a combinatorial embedding method for open-set recognition that leverages both labeled and unlabeled data to identify and cluster novel classes, improving recognition beyond known categories.

Contribution

It presents a novel combinatorial learning approach that combines supervised meta-classifiers and unsupervised relation learning to discover and represent unseen classes.

Findings

Significant performance improvements on image retrieval tasks.

Effective clustering of unseen classes in benchmark datasets.

Robustness of representations through pairwise relation learning.

Abstract

Visual recognition tasks are often limited to dealing with a small subset of classes simply because the labels for the remaining classes are unavailable. We are interested in identifying novel concepts in a dataset through representation learning based on both labeled and unlabeled examples, and extending the horizon of recognition to both known and novel classes. To address this challenging task, we propose a combinatorial learning approach, which naturally clusters the examples in unseen classes using the compositional knowledge given by multiple supervised meta-classifiers on heterogeneous label spaces. The representations given by the combinatorial embedding are made more robust by unsupervised pairwise relation learning. The proposed algorithm discovers novel concepts via a joint optimization for enhancing the discrimitiveness of unseen classes as well as learning the representations of known classes generalizable to novel ones. Our extensive experiments demonstrate remarkable performance gains by the proposed approach on public datasets for image retrieval and image categorization with novel class discovery.