VIAssist: Adapting Multi-modal Large Language Models for Users with Visual Impairments
This addresses the problem of visual accessibility for an estimated 2.2 billion visually impaired people worldwide, representing an incremental adaptation of existing MLLM technology.
The paper tackles the challenge of enabling visually impaired individuals to use multi-modal large language models (MLLMs) for visual-question answering by developing VIAssist, which identifies undesired images and provides actions, resulting in improvements of +0.21 BERTScore and +0.31 ROUGE over the baseline.
Individuals with visual impairments, encompassing both partial and total difficulties in visual perception, are referred to as visually impaired (VI) people. An estimated 2.2 billion individuals worldwide are affected by visual impairments. Recent advancements in multi-modal large language models (MLLMs) have showcased their extraordinary capabilities across various domains. It is desirable to help VI individuals with MLLMs' great capabilities of visual understanding and reasoning. However, it is challenging for VI people to use MLLMs due to the difficulties in capturing the desirable images to fulfill their daily requests. For example, the target object is not fully or partially placed in the image. This paper explores how to leverage MLLMs for VI individuals to provide visual-question answers. VIAssist can identify undesired images and provide detailed actions. Finally, VIAssist can provide reliable answers to users' queries based on the images. Our results show that VIAssist provides +0.21 and +0.31 higher BERTScore and ROUGE scores than the baseline, respectively.