Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding

TL;DR

This paper introduces a neural-symbolic approach to visual question answering that combines deep learning with symbolic reasoning, achieving high accuracy, efficiency, and interpretability on complex reasoning tasks.

Contribution

It presents a novel neural-symbolic VQA system that integrates scene understanding with symbolic program execution, enhancing robustness, efficiency, and transparency.

Findings

Achieves 99.8% accuracy on CLEVR dataset

Requires less training data and storage

Provides interpretable reasoning steps

Abstract

We marry two powerful ideas: deep representation learning for visual recognition and language understanding, and symbolic program execution for reasoning. Our neural-symbolic visual question answering (NS-VQA) system first recovers a structural scene representation from the image and a program trace from the question. It then executes the program on the scene representation to obtain an answer. Incorporating symbolic structure as prior knowledge offers three unique advantages. First, executing programs on a symbolic space is more robust to long program traces; our model can solve complex reasoning tasks better, achieving an accuracy of 99.8% on the CLEVR dataset. Second, the model is more data- and memory-efficient: it performs well after learning on a small number of training data; it can also encode an image into a compact representation, requiring less storage than existing methods for offline question answering. Third, symbolic program execution offers full transparency to the reasoning process; we are thus able to interpret and diagnose each execution step.