RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training
This work addresses data scarcity in biomedical VQA, an incremental improvement for researchers and practitioners in medical AI.
The paper tackles the problem of limited data in biomedical visual question answering (VQA) by proposing RAMM, a retrieval-augmented pretrain-and-finetune paradigm, which achieves state-of-the-art performance on multiple biomedical VQA datasets such as Med-VQA2019, Med-VQA2021, VQARAD, and SLAKE.
Vision-and-language multi-modal pretraining and fine-tuning have shown great success in visual question answering (VQA). Compared to general domain VQA, the performance of biomedical VQA suffers from limited data. In this paper, we propose a retrieval-augmented pretrain-and-finetune paradigm named RAMM for biomedical VQA to overcome the data limitation issue. Specifically, we collect a new biomedical dataset named PMCPM which offers patient-based image-text pairs containing diverse patient situations from PubMed. Then, we pretrain the biomedical multi-modal model to learn visual and textual representation for image-text pairs and align these representations with image-text contrastive objective (ITC). Finally, we propose a retrieval-augmented method to better use the limited data. We propose to retrieve similar image-text pairs based on ITC from pretraining datasets and introduce a novel retrieval-attention module to fuse the representation of the image and the question with the retrieved images and texts. Experiments demonstrate that our retrieval-augmented pretrain-and-finetune paradigm obtains state-of-the-art performance on Med-VQA2019, Med-VQA2021, VQARAD, and SLAKE datasets. Further analysis shows that the proposed RAMM and PMCPM can enhance biomedical VQA performance compared with previous resources and methods. We will open-source our dataset, codes, and pretrained model.