Saved in:
Bibliographic Details
Main Authors: Qiu, Liping, Zhang, Qin, Chen, Xiaojun, Cai, Shaotian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.11740
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917572160520192
author Qiu, Liping
Zhang, Qin
Chen, Xiaojun
Cai, Shaotian
author_facet Qiu, Liping
Zhang, Qin
Chen, Xiaojun
Cai, Shaotian
contents Recently, the cross-modal pretraining model has been employed to produce meaningful pseudo-labels to supervise the training of an image clustering model. However, numerous erroneous alignments in a cross-modal pre-training model could produce poor-quality pseudo-labels and degrade clustering performance. To solve the aforementioned issue, we propose a novel \textbf{Multi-level Cross-modal Alignment} method to improve the alignments in a cross-modal pretraining model for downstream tasks, by building a smaller but better semantic space and aligning the images and texts in three levels, i.e., instance-level, prototype-level, and semantic-level. Theoretical results show that our proposed method converges, and suggests effective means to reduce the expected clustering risk of our method. Experimental results on five benchmark datasets clearly show the superiority of our new method.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11740
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-level Cross-modal Alignment for Image Clustering
Qiu, Liping
Zhang, Qin
Chen, Xiaojun
Cai, Shaotian
Computer Vision and Pattern Recognition
Machine Learning
Recently, the cross-modal pretraining model has been employed to produce meaningful pseudo-labels to supervise the training of an image clustering model. However, numerous erroneous alignments in a cross-modal pre-training model could produce poor-quality pseudo-labels and degrade clustering performance. To solve the aforementioned issue, we propose a novel \textbf{Multi-level Cross-modal Alignment} method to improve the alignments in a cross-modal pretraining model for downstream tasks, by building a smaller but better semantic space and aligning the images and texts in three levels, i.e., instance-level, prototype-level, and semantic-level. Theoretical results show that our proposed method converges, and suggests effective means to reduce the expected clustering risk of our method. Experimental results on five benchmark datasets clearly show the superiority of our new method.
title Multi-level Cross-modal Alignment for Image Clustering
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2401.11740