NOVEL CLASS DISCOVERY: A DEPENDENCY APPROACH

Research output: Chapter in Book/Report/Conference proceedingConference paper

122 Downloads (Pure)

Abstract

Supervised and semi-supervised algorithms have been designed under a closed-world setting, with the assumption that unlabeled data consists of classes previously seen in labeled training data. However, real world is inherently open set where this assumption is often violated, and thus novel data may be encountered in test data. In this paper, we look at the problem where the model is required to discover novel classes never encountered in the labeled set. We propose a dependency measure based on Squared Mutual Information (SMI) where we simultaneously learn to classify and cluster the data. Our experiments show that our approach is able to achieve competitive performance on CIFAR and Imagenet datasets.
Original languageEnglish
Title of host publicationIEEE International Conference on Acoustics, Speech and Signal Processing
PublisherIEEE Signal Processing Society
Pages2525-2528
Number of pages4
ISBN (Electronic)9781665405409
ISBN (Print)9781665405416
DOIs
Publication statusPublished - 2022
Event2022 International Conference on Acoustics, Speech, and Signal Processing - , Singapore
Duration: 22 May 202227 May 2022

Publication series

NameInternational Conference on Acoustics, Speech and Signal Processing

Conference

Conference2022 International Conference on Acoustics, Speech, and Signal Processing
Country/TerritorySingapore
Period22/05/2227/05/22

Fingerprint

Dive into the research topics of 'NOVEL CLASS DISCOVERY: A DEPENDENCY APPROACH'. Together they form a unique fingerprint.

Cite this