KTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA

The open-ended question answering task of Text-VQA requires reading and reasoning about local, often previously unseen, scene-text content of an image. We address this zero-shot nature of the problem by proposing the generalized use of external knowledge to augment our understanding of the said scene-text. We design a framework to extract, validate, and reason with knowledge using a standard multimodal transformer for vision language understanding tasks. Through empirical evidence and qualitative results, we demonstrate how external knowledge can highlight instance-only cues and thus help deal with training data bias, improve answer entity type correctness, and detect multiword named entities. We generate results comparable to the state-of-the-art on three publicly available datasets, under the constraints of similar upstream OCR systems and training data.