CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension

TL;DR

This paper introduces CK-Transformer, a novel model that integrates commonsense knowledge into transformers to improve referring expression comprehension, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper presents a new framework that effectively incorporates commonsense knowledge into transformers for better object localization in referring expressions.

Findings

Achieves 3.14% higher accuracy than previous methods.

Effectively integrates commonsense knowledge into visual-language reasoning.

Sets new state-of-the-art on multiple benchmarks.

Abstract

The task of multimodal referring expression comprehension (REC), aiming at localizing an image region described by a natural language expression, has recently received increasing attention within the research comminity. In this paper, we specifically focus on referring expression comprehension with commonsense knowledge (KB-Ref), a task which typically requires reasoning beyond spatial, visual or semantic information. We propose a novel framework for Commonsense Knowledge Enhanced Transformers (CK-Transformer) which effectively integrates commonsense knowledge into the representations of objects in an image, facilitating identification of the target objects referred to by the expressions. We conduct extensive experiments on several benchmarks for the task of KB-Ref. Our results show that the proposed CK-Transformer achieves a new state of the art, with an absolute improvement of 3.14% accuracy over the existing state of the art.