Timezone: »
Visual commonsense reasoning task aims at leading the research field into solving cognition-level reasoning with the ability to predict correct answers and meanwhile providing convincing reasoning paths, resulting in three sub-tasks i.e., Q->A, QA->R and Q->AR. It poses great challenges over the proper semantic alignment between vision and linguistic domains and knowledge reasoning to generate persuasive reasoning paths. Existing works either resort to a powerful end-to-end network that cannot produce interpretable reasoning paths or solely explore intra-relationship of visual objects (homogeneous graph) while ignoring the cross-domain semantic alignment among visual concepts and linguistic words. In this paper, we propose a new Heterogeneous Graph Learning (HGL) framework for seamlessly integrating the intra-graph and inter-graph reasoning in order to bridge the vision and language domain. Our HGL consists of a primal vision-to-answer heterogeneous graph (VAHG) module and a dual question-to-answer heterogeneous graph (QAHG) module to interactively refine reasoning paths for semantic agreement. Moreover, our HGL integrates a contextual voting module to exploit a long-range visual context for better global reasoning. Experiments on the large-scale Visual Commonsense Reasoning benchmark demonstrate the superior performance of our proposed modules on three tasks (improving 5% accuracy on Q->A, 3.5% on QA->R, 5.8% on Q->AR).
Author Information
Weijiang Yu (Sun Yat-sen University)
Jingwen Zhou (Sun Yat-sen University)
Weihao Yu (Sun Yat-sen University)
Xiaodan Liang (Sun Yat-sen University)
Nong Xiao (Sun Yat-sen University)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Spotlight: Heterogeneous Graph Learning for Visual Commonsense Reasoning »
Thu Dec 12th 12:45 -- 12:50 AM Room West Ballroom A + B
More from the Same Authors
-
2020 Poster: AutoSync: Learning to Synchronize for Data-Parallel Distributed Deep Learning »
Hao Zhang · Yuan Li · Zhijie Deng · Xiaodan Liang · Lawrence Carin · Eric Xing -
2020 Poster: Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation »
Yangxin Wu · Gengwei Zhang · Hang Xu · Xiaodan Liang · Liang Lin -
2020 Poster: Towards Interpretable Natural Language Understanding with Explanations as Latent Variables »
Wangchunshu Zhou · Jinyi Hu · Hanlin Zhang · Xiaodan Liang · Maosong Sun · Chenyan Xiong · Jian Tang -
2020 Poster: ConvBERT: Improving BERT with Span-based Dynamic Convolution »
Zi-Hang Jiang · Weihao Yu · Daquan Zhou · Yunpeng Chen · Jiashi Feng · Shuicheng Yan -
2020 Spotlight: ConvBERT: Improving BERT with Span-based Dynamic Convolution »
Zi-Hang Jiang · Weihao Yu · Daquan Zhou · Yunpeng Chen · Jiashi Feng · Shuicheng Yan -
2018 Poster: Symbolic Graph Reasoning Meets Convolutions »
Xiaodan Liang · Zhiting Hu · Hao Zhang · Liang Lin · Eric Xing -
2018 Poster: Deep Generative Models with Learnable Knowledge Constraints »
Zhiting Hu · Zichao Yang · Russ Salakhutdinov · LIANHUI Qin · Xiaodan Liang · Haoye Dong · Eric Xing -
2018 Poster: Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation »
Yuan Li · Xiaodan Liang · Zhiting Hu · Eric Xing -
2018 Poster: Hybrid Knowledge Routed Modules for Large-scale Object Detection »
ChenHan Jiang · Hang Xu · Xiaodan Liang · Liang Lin -
2018 Poster: Soft-Gated Warping-GAN for Pose-Guided Person Image Synthesis »
Haoye Dong · Xiaodan Liang · Ke Gong · Hanjiang Lai · Jia Zhu · Jian Yin -
2017 Poster: Structured Generative Adversarial Networks »
Zhijie Deng · Hao Zhang · Xiaodan Liang · Luona Yang · Shizhen Xu · Jun Zhu · Eric Xing -
2016 Poster: Tree-Structured Reinforcement Learning for Sequential Object Localization »
Zequn Jie · Xiaodan Liang · Jiashi Feng · Xiaojie Jin · Wen Lu · Shuicheng Yan