AISciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification

ICLR 2025 Conference Submission13528 Authors

28 Sept 2024 (modified: 20 Nov 2024)ICLR 2025 Conference SubmissionEveryoneRevisionsBibTeXCC BY 4.0
Keywords: computer vision, large language models, scientific application, retrieval augmented generation, agent systems
Abstract: Trust and interpretability are crucial for the use of Artificial Intelligence (AI) in scientific research, but current models often operate as black boxes offering limited transparency and justifications for their outputs. Motivated by this problem, we introduce AiSciVision, a framework that specializes Large Multimodal Models (LMMs) into interactive research partners and classification models for image classification tasks in niche scientific domains. Our framework uses two key components: (1) Visual Retrieval-Augmented Generation (VisRAG) and (2) domain-specific tools utilized in an agentic workflow. To classify a target image, AiSciVision first retrieves the most similar positive and negative labeled images as context for the LMM. Then the LMM agent actively selects and applies tools to manipulate and inspect the target image over multiple rounds, refining its analysis before making a final prediction. These VisRAG and tooling components are designed to mirror the processes of domain experts, as humans often compare new data to similar examples and use specialized tools to manipulate and inspect images before arriving at a conclusion. Each inference produces both a prediction and a natural language transcript detailing the reasoning and tool usage that led to the prediction. We evaluate AiSciVision on three real-world scientific image classification datasets: detecting the presence of aquaculture ponds, diseased eelgrass, and solar panels. Across these datasets, our method outperforms fully supervised models in low and full-labeled data settings. AiSciVision is actively deployed in real-world use, specifically for aquaculture research, through a dedicated web application that displays and allows the expert users to converse with the transcripts. This work represents a crucial step toward AI systems that are both interpretable and effective, advancing their use in scientific research and scientific discovery.
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13528
Loading