Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
This work addresses the problem of enabling more flexible and accurate medical diagnoses through open-ended VQA, representing an incremental improvement over closed-set classification methods.
The authors tackled open-ended medical visual question answering by framing it as a generative task using pre-trained language models, and their method outperformed existing approaches on benchmarks like Slake, OVQA, and PathVQA while being computationally efficient.
Medical Visual Question Answering (VQA) is an important challenge, as it would lead to faster and more accurate diagnoses and treatment decisions. Most existing methods approach it as a multi-class classification problem, which restricts the outcome to a predefined closed-set of curated answers. We focus on open-ended VQA and motivated by the recent advances in language models consider it as a generative task. Leveraging pre-trained language models, we introduce a novel method particularly suited for small, domain-specific, medical datasets. To properly communicate the medical images to the language model, we develop a network that maps the extracted visual features to a set of learnable tokens. Then, alongside the question, these learnable tokens directly prompt the language model. We explore recent parameter-efficient fine-tuning strategies for language models, which allow for resource- and data-efficient fine-tuning. We evaluate our approach on the prime medical VQA benchmarks, namely, Slake, OVQA and PathVQA. The results demonstrate that our approach outperforms existing methods across various training settings while also being computationally efficient.