| Summary: | The open-ended question answering task of Text-VQA often requires reading and reasoning about <italic>rarely seen or completely unseen</italic> scene text content of an image. We address this zero-shot nature of the task by proposing the generalized use of external knowledge to augment our understanding of the 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.
|
|---|