Medical VQA
Home > Case Study > SMAAS
Medical VQA
Overview
Develop a Visual question answering LLM which takes image and question as inputs and returns an answer as output. Developed a multi-modal transformer model for Medical Visual Question Answering (MVQA) using the PathVQA dataset. Fine-tuned a pre-trained BLIP model on proprietary data to enhance accuracy and context-awareness in medical question answering
Kindly fill up the form below to continue download
By clicking on the button above, you agree to Park Intelli solutions Terms, Privacy and Cookie Policies. You also agree to receive future communications from us. You can unsubscribe anytime.
Get Started
Ready to build a more predictable and consistent client pipeline?
Kindly get in touch with us for business requirements to facilitate a personalized assistance from Parki Solutions.
