EchoSight: Advancing Visual-Language Models with Wiki Knowledge
- URL: http://arxiv.org/abs/2407.12735v3
- Date: Tue, 5 Nov 2024 07:24:15 GMT
- Title: EchoSight: Advancing Visual-Language Models with Wiki Knowledge
- Authors: Yibin Yan, Weidi Xie,
- Abstract summary: We introduce EchoSight, a novel framework for knowledge-based Visual Question Answering.
To strive for high-performing retrieval, EchoSight first searches wiki articles by using visual-only information.
Our experimental results on the Encyclopedic VQA and InfoSeek datasets demonstrate that EchoSight establishes new state-of-the-art results in knowledge-based VQA.
- Score: 39.02148880719576
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Knowledge-based Visual Question Answering (KVQA) tasks require answering questions about images using extensive background knowledge. Despite significant advancements, generative models often struggle with these tasks due to the limited integration of external knowledge. In this paper, we introduce EchoSight, a novel multimodal Retrieval-Augmented Generation (RAG) framework that enables large language models (LLMs) to answer visual questions requiring fine-grained encyclopedic knowledge. To strive for high-performing retrieval, EchoSight first searches wiki articles by using visual-only information, subsequently, these candidate articles are further reranked according to their relevance to the combined text-image query. This approach significantly improves the integration of multimodal knowledge, leading to enhanced retrieval outcomes and more accurate VQA responses. Our experimental results on the Encyclopedic VQA and InfoSeek datasets demonstrate that EchoSight establishes new state-of-the-art results in knowledge-based VQA, achieving an accuracy of 41.8% on Encyclopedic VQA and 31.3% on InfoSeek.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.