Modular Visual Question Answering via Code Generation
This addresses visual question answering for AI systems by providing a modular, training-free approach, though it is incremental as it builds on existing pre-trained models and in-context learning.
The paper tackles visual question answering by formulating it as modular code generation, improving accuracy on COVR by at least 3% and on GQA by roughly 2% compared to a few-shot baseline.
We present a framework that formulates visual question answering as modular code generation. In contrast to prior work on modular approaches to VQA, our approach requires no additional training and relies on pre-trained language models (LMs), visual models pre-trained on image-caption pairs, and fifty VQA examples used for in-context learning. The generated Python programs invoke and compose the outputs of the visual models using arithmetic and conditional logic. Our approach improves accuracy on the COVR dataset by at least 3% and on the GQA dataset by roughly 2% compared to the few-shot baseline that does not employ code generation.