PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers
This work addresses the problem of exacting retrieval tasks in multimodal AI for researchers and practitioners, though it appears incremental as it builds on an existing method.
The authors tackled the challenge of Knowledge-based Visual Question Answering (KB-VQA) by developing PreFLMR, a pre-trained version of the Fine-grained Late-interaction Multi-modal Retriever, achieving new state-of-the-art results across multiple tasks.
Large Multimodal Models (LMMs) excel in natural language and visual understanding but are challenged by exacting tasks such as Knowledge-based Visual Question Answering (KB-VQA) which involve the retrieval of relevant information from document collections to use in shaping answers to questions. We present an extensive training and evaluation framework, M2KR, for KB-VQA. M2KR contains a collection of vision and language tasks which we have incorporated into a single suite of benchmark tasks for training and evaluating general-purpose multi-modal retrievers. We use M2KR to develop PreFLMR, a pre-trained version of the recently developed Fine-grained Late-interaction Multi-modal Retriever (FLMR) approach to KB-VQA, and we report new state-of-the-art results across a range of tasks. We also present investigations into the scaling behaviors of PreFLMR intended to be useful in future developments in general-purpose multi-modal retrievers.