Hierarchical Transformer Encoder With Structured Representation for Abstract Reasoning

IEEE Access

卷:8

Jinwon An¹  Sungzoon Cho¹ 

[1] Department of Industrial Engineering, Seoul National University, Seoul, South Korea;

关键词: Abstract reasoning;    object detection;    Raven’s progressive matrices;    self-attention;    structured representations;    transformer;   

DOI  :  10.1109/ACCESS.2020.3035463

来源: DOAJ

【 摘 要 】

Abstract reasoning is one of the defining characteristics of human intelligence and can be estimated by visual IQ tests such as Raven's Progressive Matrices. In this paper, we propose using a hierarchical Transformer encoder with structured representation that employs a novel neural network architecture to improve both perception and reasoning in a visual IQ test. For perception, we used object detection models to extract the structured features. For reasoning, we used the Transformer encoder in a hierarchical manner that fits the structure of Raven's Progressive Matrices. Experimental results on the RAVEN dataset, which is one of the major large-scale datasets on Raven's Progressive Matrices, showed that our proposed architecture achieved an overall accuracy of 99.62%, which is an improvement of more than 8% points over CoPINet, the present-day, state-of-the-art neural network model.

【 授权许可】

Unknown