!!Activities per year
Abstract
Image clustering divides a collection of images into meaningful groups, typically interpreted post-hoc via human-given annotations. Those are usually in the form of text, begging the question of using text as an abstraction for image clustering. Current image clustering methods, however, neglect the use of generated textual descriptions. We, therefore, propose Text-Guided Image Clustering, i.e., generating text using image captioning and visual question-answering (VQA) models and subsequently clustering the generated text. Further, we introduce a novel approach to inject task- or domain knowledge for clustering by prompting VQA models. Across eight diverse image clustering datasets, our results show that the obtained text representations often outperform image features. Additionally, we propose a counting-based cluster explainability method. Our evaluations show that the derived keyword-based explanations describe clusters better than the respective cluster accuracy suggests. Overall, this research challenges traditional approaches and paves the way for a paradigm shift in image clustering, using generated text.
| Originalsprache | Englisch |
|---|---|
| Titel | 18th Conference of the European Chapter of the Association for Computational Linguistics |
| Untertitel | Proceedings of the Conference, Vol. 1 (Long Papers) |
| Redakteure*innen | Yvette Graham, Matthew Purver |
| Erscheinungsort | Kerrville |
| Verlag | ACL Anthology |
| Seiten | 2960-2976 |
| ISBN (Print) | 979-8-89176-088-2 |
| DOIs | |
| Publikationsstatus | Veröffentlicht - 2024 |
| Veranstaltung | 18th Conference of the European Chapter of the Association for Computational Linguistics - , Malta Dauer: 17 März 2024 → 22 März 2024 https://2024.eacl.org/ |
Konferenz
| Konferenz | 18th Conference of the European Chapter of the Association for Computational Linguistics |
|---|---|
| Kurztitel | EACL 2024 |
| Land/Gebiet | Malta |
| Zeitraum | 17/03/24 → 22/03/24 |
| Internetadresse |
ÖFOS 2012
- 102019 Machine Learning
- 602011 Computerlinguistik
Fingerprint
Untersuchen Sie die Forschungsthemen von „Text-Guided Image Clustering“. Zusammen bilden sie einen einzigartigen Fingerprint.Aktivitäten
- 1 Vortrag
-
Text-Guided Image Clustering
Stephan, A. (Vortragende*r) & Roth, B. (Vortragende*r)
2024Aktivität: Vorträge › Vortrag › Science to Science
Zitationsweisen
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver