文章基本信息

标题：Semantic representation for visual reasoning
本地全文：下载
作者：Xubin Ni ; Lirong Yin ; Xiaobing Chen 等
期刊名称：MATEC Web of Conferences
电子版ISSN：2261-236X
出版年度：2019
卷号：277
DOI：10.1051/matecconf/201927702006
语种：English
出版社：EDP Sciences
摘要：In the field of visual reasoning, image features are widely used as the input of neural networks to get answers. However, image features are too redundant to learn accurate characterizations for regular networks. While in human reasoning, abstract description is usually constructed to avoid irrelevant details. Inspired by this, a higher-level representation named semantic representation is introduced in this paper to make visual reasoning more efficient. The idea of the Gram matrix used in the neural style transfer research is transferred here to build a relation matrix which enables the related information between objects to be better represented. The model using semantic representation as input outperforms the same model using image features as input which verifies that more accurate results can be obtained through the introduction of high-level semantic representation in the field of visual reasoning.