CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension
This addresses the challenge of localizing image regions using natural language expressions that require commonsense reasoning, representing an incremental advance in multimodal AI.
The paper tackles the problem of referring expression comprehension with commonsense knowledge (KB-Ref) by proposing CK-Transformer, a framework that integrates commonsense knowledge into object representations, achieving a new state of the art with a 3.14% accuracy improvement.
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.