Multi-Task Convolutional Neural Network Leading to High Performance and Interpretability via Attribute Estimation

Keisuke MAEDA  Kazaha HORII  Takahiro OGAWA  Miki HASEYAMA  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E103-A    No.12    pp.1609-1612
Publication Date: 2020/12/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.2020SML0006
Type of Manuscript: Special Section LETTER (Special Section on Smart Multimedia & Communication Systems)
Category: Neural Networks and Bioengineering
multi-task convolutional neural network,  image classification,  attribute estimation,  interpretability,  

Full Text: PDF(930.7KB)>>
Buy this Article

A multi-task convolutional neural network leading to high performance and interpretability via attribute estimation is presented in this letter. Our method can provide interpretation of the classification results of CNNs by outputting attributes that explain elements of objects as a judgement reason of CNNs in the middle layer. Furthermore, the proposed network uses the estimated attributes for the following prediction of classes. Consequently, construction of a novel multi-task CNN with improvements in both of the interpretability and classification performance is realized.