Home | Publications | SML+24

Text-Guided Alternative Image Clustering

MCML Authors

Abstract

Traditional image clustering techniques only find a single grouping within visual data. In particular, they do not provide a possibility to explicitly define multiple types of clustering. This work explores the potential of large vision-language models to facilitate alternative image clustering. We propose Text-Guided Alternative Image Consensus Clustering (TGAICC), a novel approach that leverages user-specified interests via prompts to guide the discovery of diverse clusterings. To achieve this, it generates a clustering for each prompt, groups them using hierarchical clustering, and then aggregates them using consensus clustering. TGAICC outperforms image- and text-based baselines on four alternative image clustering benchmark datasets. Furthermore, using count-based word statistics, we are able to obtain text-based explanations of the alternative clusterings. In conclusion, our research illustrates how contemporary large vision-language models can transform explanatory data analysis, enabling the generation of insightful, customizable, and diverse image clusterings.

inproceedings SML+24

RepL4NLP-2024 @ACL 2024

9th Workshop on Representation Learning for NLP at the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand, Aug 11-16, 2024.

Authors

A. Stephan • L. Miklautz • C. Leiber • P. H. Araujo • D. Répás • C. Plant • B. Roth

Links

URL

Research Area

 A3 | Computational Models

BibTeXKey: SML+24

#p-seidl
Back to Top