Timezone: »

 
IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
Pan Lu · Liang Qiu · Jiaqi Chen · Tanglin Xia · Yizhou Zhao · Wei Zhang · Zhou Yu · Xiaodan Liang · Song-Chun Zhu

@
in Dataset and Benchmark Poster Session 2 »

Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images. However, aside from natural images, abstract diagrams with semantic richness are still understudied in visual understanding and reasoning research. In this work, we introduce a new challenge of Icon Question Answering (IconQA) with the goal of answering a question in an icon image context. We release IconQA, a large-scale dataset that consists of 107,439 questions and three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. The IconQA dataset is inspired by real-world diagram word problems that highlight the importance of abstract diagram understanding and comprehensive cognitive reasoning. Thus, IconQA requires not only perception skills like object recognition and text understanding, but also diverse cognitive reasoning skills, such as geometric reasoning, commonsense reasoning, and arithmetic reasoning. To facilitate potential IconQA models to learn semantic representations for icon images, we further release an icon dataset Icon645 which contains 645,687 colored icons on 377 classes. We conduct extensive user studies and blind experiments and reproduce a wide range of advanced VQA methods to benchmark the IconQA task. Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset. IconQA and Icon645 are available at https://iconqa.github.io.

[ Chat] 

Author Information

Pan Lu (University of California, Los Angeles)
Liang Qiu (University of California, Los Angeles)

My name is Liang Qiu. I am doing research in the Center for Vision, Cognition, Learning, and Autonomy (VCLA) at UCLA. I design algorithms and write code to build multi-modal socially intelligent interactive systems. My research interests include natural language processing, dialogue management, computational sociology, and medical AI.

Jiaqi Chen (SUN YAT-SEN UNIVERSITY)
Tanglin Xia (UCLA)
Yizhou Zhao (University of California, Los Angeles)
Wei Zhang (East China Normal University)
Zhou Yu (University of California, Davis)
Xiaodan Liang (Sun Yat-sen University)
Song-Chun Zhu (UCLA)

More from the Same Authors