CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hao, Shaozhe, Han, Kai, Wong, Kwan-Yee K.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917621267431424
author Hao, Shaozhe
Han, Kai
Wong, Kwan-Yee K.
author_facet Hao, Shaozhe
Han, Kai
Wong, Kwan-Yee K.
contents We tackle the issue of generalized category discovery (GCD). GCD considers the open-world problem of automatically clustering a partially labelled dataset, in which the unlabelled data may contain instances from both novel categories and labelled classes. In this paper, we address the GCD problem with an unknown category number for the unlabelled data. We propose a framework, named CiPR, to bootstrap the representation by exploiting Cross-instance Positive Relations in the partially labelled data for contrastive learning, which have been neglected in existing methods. To obtain reliable cross-instance relations to facilitate representation learning, we introduce a semi-supervised hierarchical clustering algorithm, named selective neighbor clustering (SNC), which can produce a clustering hierarchy directly from the connected components of a graph constructed from selective neighbors. We further present a method to estimate the unknown class number using SNC with a joint reference score that considers clustering indexes of both labelled and unlabelled data, and extend SNC to allow label assignment for the unlabelled instances with a given class number. We thoroughly evaluate our framework on public generic image recognition datasets and challenging fine-grained datasets, and establish a new state-of-the-art. Code: https://github.com/haoosz/CiPR
format Preprint
id arxiv_https___arxiv_org_abs_2304_06928
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery
Hao, Shaozhe
Han, Kai
Wong, Kwan-Yee K.
Computer Vision and Pattern Recognition
Artificial Intelligence
We tackle the issue of generalized category discovery (GCD). GCD considers the open-world problem of automatically clustering a partially labelled dataset, in which the unlabelled data may contain instances from both novel categories and labelled classes. In this paper, we address the GCD problem with an unknown category number for the unlabelled data. We propose a framework, named CiPR, to bootstrap the representation by exploiting Cross-instance Positive Relations in the partially labelled data for contrastive learning, which have been neglected in existing methods. To obtain reliable cross-instance relations to facilitate representation learning, we introduce a semi-supervised hierarchical clustering algorithm, named selective neighbor clustering (SNC), which can produce a clustering hierarchy directly from the connected components of a graph constructed from selective neighbors. We further present a method to estimate the unknown class number using SNC with a joint reference score that considers clustering indexes of both labelled and unlabelled data, and extend SNC to allow label assignment for the unlabelled instances with a given class number. We thoroughly evaluate our framework on public generic image recognition datasets and challenging fine-grained datasets, and establish a new state-of-the-art. Code: https://github.com/haoosz/CiPR
title CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2304.06928