Online Continuous Generalized Category Discovery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Park, Keon-Hee, Lee, Hakyung, Song, Kyungwoo, Park, Gyeong-Moon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917757668294656
author Park, Keon-Hee
Lee, Hakyung
Song, Kyungwoo
Park, Gyeong-Moon
author_facet Park, Keon-Hee
Lee, Hakyung
Song, Kyungwoo
Park, Gyeong-Moon
contents With the advancement of deep neural networks in computer vision, artificial intelligence (AI) is widely employed in real-world applications. However, AI still faces limitations in mimicking high-level human capabilities, such as novel category discovery, for practical use. While some methods utilizing offline continual learning have been proposed for novel category discovery, they neglect the continuity of data streams in real-world settings. In this work, we introduce Online Continuous Generalized Category Discovery (OCGCD), which considers the dynamic nature of data streams where data can be created and deleted in real time. Additionally, we propose a novel method, DEAN, Discovery via Energy guidance and feature AugmentatioN, which can discover novel categories in an online manner through energy-guided discovery and facilitate discriminative learning via energy-based contrastive loss. Furthermore, DEAN effectively pseudo-labels unlabeled data through variance-based feature augmentation. Experimental results demonstrate that our proposed DEAN achieves outstanding performance in proposed OCGCD scenario.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13492
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Online Continuous Generalized Category Discovery
Park, Keon-Hee
Lee, Hakyung
Song, Kyungwoo
Park, Gyeong-Moon
Computer Vision and Pattern Recognition
With the advancement of deep neural networks in computer vision, artificial intelligence (AI) is widely employed in real-world applications. However, AI still faces limitations in mimicking high-level human capabilities, such as novel category discovery, for practical use. While some methods utilizing offline continual learning have been proposed for novel category discovery, they neglect the continuity of data streams in real-world settings. In this work, we introduce Online Continuous Generalized Category Discovery (OCGCD), which considers the dynamic nature of data streams where data can be created and deleted in real time. Additionally, we propose a novel method, DEAN, Discovery via Energy guidance and feature AugmentatioN, which can discover novel categories in an online manner through energy-guided discovery and facilitate discriminative learning via energy-based contrastive loss. Furthermore, DEAN effectively pseudo-labels unlabeled data through variance-based feature augmentation. Experimental results demonstrate that our proposed DEAN achieves outstanding performance in proposed OCGCD scenario.
title Online Continuous Generalized Category Discovery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.13492