OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
arXiv:1906.00067
Abstract
Visual Question Answering (VQA) in its ideal form lets us study reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most VQA benchmarks to date are focused on questions such as simple counting, visual attributes, and object detection that do not require reasoning or knowledge beyond what is in the image. In this paper, we address the task of knowledge-based visual question answering and provide a benchmark, called OK-VQA, where the image content is not sufficient to answer the questions, encouraging methods that rely on external knowledge resources. Our new dataset includes more than 14,000 questions that require external knowledge to answer. We show that the performance of the state-of-the-art VQA models degrades drastically in this new setting. Our analysis shows that our knowledge-based VQA task is diverse, difficult, and large compared to previous knowledge-based VQA datasets. We hope that this dataset enables researchers to open up new avenues for research in this domain. See http://okvqa.allenai.org to download and browse the dataset.
arXiv commentCVPR 2019
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Dynamic Memory Networks for Visual and Textual Question Answering
- End-To-End Memory Networks
- Exploring Models and Data for Image Question Answering
- A Multi-World Approach to Question Answering about Real-World Scenes based on Uncertain Input
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
- Pythia v0.1: the Winning Entry to the VQA Challenge 2018
- An Implementation of Faster RCNN with Study for Region Sampling
- Explicit Knowledge-based Reasoning for Visual Question Answering
- Bilinear Attention Networks
- Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
- FVQA: Fact-based Visual Question Answering