Understanding Museum Exhibits using Vision-Language Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911143047462912 |
|---|---|
| author | Balauca, Ada-Astrid Garai, Sanjana Balauca, Stefan Shetty, Rasesh Udayakumar Agrawal, Naitik Shah, Dhwanil Subhashbhai Fu, Yuqian Wang, Xi Toutanova, Kristina Paudel, Danda Pani Van Gool, Luc |
| author_facet | Balauca, Ada-Astrid Garai, Sanjana Balauca, Stefan Shetty, Rasesh Udayakumar Agrawal, Naitik Shah, Dhwanil Subhashbhai Fu, Yuqian Wang, Xi Toutanova, Kristina Paudel, Danda Pani Van Gool, Luc |
| contents | Museums serve as repositories of cultural heritage and historical artifacts from diverse epochs, civilizations, and regions, preserving well-documented collections that encapsulate vast knowledge, which, when systematically structured into large-scale datasets, can train specialized models. Visitors engage with exhibits through curiosity and questions, making expert domain-specific models essential for interactive query resolution and gaining historical insights. Understanding exhibits from images requires analyzing visual features and linking them to historical knowledge to derive meaningful correlations. We facilitate such reasoning by (a) collecting and curating a large-scale dataset of 65M images and 200M question-answer pairs for exhibits from all around the world; (b) training large vision-language models (VLMs) on the collected dataset; (c) benchmarking their ability on five visual question answering tasks, specifically designed to reflect real-world inquiries and challenges observed in museum settings. The complete dataset is labeled by museum experts, ensuring the quality and the practical significance of the labels. We train two VLMs from different categories: BLIP with vision-language aligned embeddings, but lacking the expressive power of large language models, and the LLaVA model, a powerful instruction-tuned LLM enriched with vision-language reasoning capabilities. Through extensive experiments, we find that while both model types effectively answer visually grounded questions, large vision-language models excel in queries requiring deeper historical context and reasoning. We further demonstrate the necessity of fine-tuning models on large-scale domain-specific datasets by showing that our fine-tuned models significantly outperform current SOTA VLMs in answering questions related to specific attributes, highlighting their limitations in handling complex, nuanced queries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01370 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding Museum Exhibits using Vision-Language Reasoning Balauca, Ada-Astrid Garai, Sanjana Balauca, Stefan Shetty, Rasesh Udayakumar Agrawal, Naitik Shah, Dhwanil Subhashbhai Fu, Yuqian Wang, Xi Toutanova, Kristina Paudel, Danda Pani Van Gool, Luc Computer Vision and Pattern Recognition Computation and Language Museums serve as repositories of cultural heritage and historical artifacts from diverse epochs, civilizations, and regions, preserving well-documented collections that encapsulate vast knowledge, which, when systematically structured into large-scale datasets, can train specialized models. Visitors engage with exhibits through curiosity and questions, making expert domain-specific models essential for interactive query resolution and gaining historical insights. Understanding exhibits from images requires analyzing visual features and linking them to historical knowledge to derive meaningful correlations. We facilitate such reasoning by (a) collecting and curating a large-scale dataset of 65M images and 200M question-answer pairs for exhibits from all around the world; (b) training large vision-language models (VLMs) on the collected dataset; (c) benchmarking their ability on five visual question answering tasks, specifically designed to reflect real-world inquiries and challenges observed in museum settings. The complete dataset is labeled by museum experts, ensuring the quality and the practical significance of the labels. We train two VLMs from different categories: BLIP with vision-language aligned embeddings, but lacking the expressive power of large language models, and the LLaVA model, a powerful instruction-tuned LLM enriched with vision-language reasoning capabilities. Through extensive experiments, we find that while both model types effectively answer visually grounded questions, large vision-language models excel in queries requiring deeper historical context and reasoning. We further demonstrate the necessity of fine-tuning models on large-scale domain-specific datasets by showing that our fine-tuned models significantly outperform current SOTA VLMs in answering questions related to specific attributes, highlighting their limitations in handling complex, nuanced queries. |
| title | Understanding Museum Exhibits using Vision-Language Reasoning |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2412.01370 |