KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA

TL;DR

KRISP advances open-domain knowledge-based VQA by combining transformer-based implicit reasoning with symbolic knowledge graph integration, significantly improving accuracy on the OK-VQA dataset.

Contribution

This work introduces KRISP, a novel method that effectively integrates implicit transformer-based reasoning with explicit symbolic knowledge representations for VQA.

Findings

KRISP outperforms state-of-the-art on OK-VQA dataset.

Symbolic knowledge integration is critical for handling rare answers.

Implicit reasoning alone is insufficient without explicit symbolic modules.

Abstract

One of the most challenging question types in VQA is when answering the question requires outside knowledge not present in the image. In this work we study open-domain knowledge, the setting when the knowledge required to answer a question is not given/annotated, neither at training nor test time. We tap into two types of knowledge representations and reasoning. First, implicit knowledge which can be learned effectively from unsupervised language pre-training and supervised training data with transformer-based models. Second, explicit, symbolic knowledge encoded in knowledge bases. Our approach combines both - exploiting the powerful implicit reasoning of transformer models for answer prediction, and integrating symbolic representations from a knowledge graph, while never losing their explicit semantics to an implicit embedding. We combine diverse sources of knowledge to cover the wide variety of knowledge needed to solve knowledge-based questions. We show our approach, KRISP (Knowledge Reasoning with Implicit and Symbolic rePresentations), significantly outperforms state-of-the-art on OK-VQA, the largest available dataset for open-domain knowledge-based VQA. We show with extensive ablations that while our model successfully exploits implicit knowledge reasoning, the symbolic answer module which explicitly connects the knowledge graph to the answer vocabulary is critical to the performance of our method and generalizes to rare answers.