How to Design Sample and Computationally Efficient VQA Models
This addresses the challenge of efficiency in multi-modal reasoning for AI applications, though it appears incremental as it extends existing models.
The paper tackled the problem of designing sample and computationally efficient models for visual question answering (VQA) by representing text as probabilistic programs and images as object-level scene graphs, achieving state-of-the-art accuracy while maintaining efficiency.
In multi-modal reasoning tasks, such as visual question answering (VQA), there have been many modeling and training paradigms tested. Previous models propose different methods for the vision and language tasks, but which ones perform the best while being sample and computationally efficient? Based on our experiments, we find that representing the text as probabilistic programs and images as object-level scene graphs best satisfy these desiderata. We extend existing models to leverage these soft programs and scene graphs to train on question answer pairs in an end-to-end manner. Empirical results demonstrate that this differentiable end-to-end program executor is able to maintain state-of-the-art accuracy while being sample and computationally efficient.