Enhancing Multimodal Large Language Models with Vision Detection Models: An Empirical Study

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. This paper presents an empirical study on enhancing MLLMs with state-of-the-art (SOTA) object detection and Optical Character Recognition models to improve fine-grained image understanding and reduce hallucination in responses. Our research investigates the embedding-based infusion of detection information, the impact of such infusion on the MLLMs' original abilities, and the interchangeability of detection models. We conduct …

art capabilities challenges character recognition cs.ai cs.cv detection fine-grained image language language models large language large language models mllms multimodal optical optical character recognition paper recognition sota state study text understanding vision visual