Text-Guided Alternative Image Clustering

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Stephan, Andreas, Miklautz, Lukas, Leiber, Collin, de Araujo, Pedro Henrique Luz, Répás, Dominik, Plant, Claudia, Roth, Benjamin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913406157586432
author Stephan, Andreas
Miklautz, Lukas
Leiber, Collin
de Araujo, Pedro Henrique Luz
Répás, Dominik
Plant, Claudia
Roth, Benjamin
author_facet Stephan, Andreas
Miklautz, Lukas
Leiber, Collin
de Araujo, Pedro Henrique Luz
Répás, Dominik
Plant, Claudia
Roth, Benjamin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18589
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text-Guided Alternative Image Clustering
Stephan, Andreas
Miklautz, Lukas
Leiber, Collin
de Araujo, Pedro Henrique Luz
Répás, Dominik
Plant, Claudia
Roth, Benjamin
Computer Vision and Pattern Recognition
Machine Learning
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.
title Text-Guided Alternative Image Clustering
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2406.18589