Generating Question Relevant Captions to Aid Visual Question Answering

Abstract

Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to improve VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. The model is trained using an existing caption dataset by automatically determining question-relevant captions using an online gradient-based method. Experimental results on the VQA v2 challenge demonstrates that our approach obtains state-of-the-art VQA performance (e.g. 68.4% on the Test-standard set using a single model) by simultaneously generating question-relevant captions.

Jialin Wu

Research Scientist

My most recent research interests is building large multimodal models that (1) are explainable generalists and (2) performan well on geographically (culturally) diversed tasks.