Text-Guided Alternative Image Clustering

MCML Authors

Collin Leiber

Dr.

* Former Member

→ Group Thomas Seidl
 Database Systems, Data Mining and AI

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.

misc

---

Preprint

Jun. 2024

---

Authors

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

---

Links

---

Research Area

 A3 | Computational Models