ViperGPT: Visual Inference via Python Execution for Reasoning
This addresses the need for more interpretable and generalizable visual reasoning systems, though it is incremental as it builds on existing code-generation and modular approaches.
The authors tackled the problem of answering visual queries by introducing ViperGPT, a framework that composes vision-and-language models via generated Python code without additional training, achieving state-of-the-art results across complex visual tasks.
Answering visual queries is a complex task that requires both visual processing and reasoning. End-to-end models, the dominant approach for this task, do not explicitly differentiate between the two, limiting interpretability and generalization. Learning modular programs presents a promising alternative, but has proven challenging due to the difficulty of learning both the programs and modules simultaneously. We introduce ViperGPT, a framework that leverages code-generation models to compose vision-and-language models into subroutines to produce a result for any query. ViperGPT utilizes a provided API to access the available modules, and composes them by generating Python code that is later executed. This simple approach requires no further training, and achieves state-of-the-art results across various complex visual tasks.