A Semantic Similarity Supervised Autoencoder for Zero-Shot Learning

被引：4

作者：

Shen, Fengli ^{[1
]}

Lu, Zhe-Ming ^{[1
]}

机构：

[1] Zhejiang Univ, Sch Aeronaut & Astronaut, Hangzhou 310027, Peoples R China

来源：

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2020年 / E103D卷 / 06期

关键词：

zero-shot learning; autoencoder; image classification;

D O I：

10.1587/transinf.2019EDL8176

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This Letter proposes a autoencoder model supervised by semantic similarity for zero-shot learning. With the help of semantic similarity vectors of seen and unseen classes and the classification branch, our experimental results on two datasets are 7.3% and 4% better than the state-of-the-art on conventional zero-shot learning in terms of the averaged top-1 accuracy.

引用

页码：1419 / 1422

页数：4

共 12 条

[1]

[Anonymous], 2019, PROC IEEECVF C COMPU

[2] Multi-modal Cycle-Consistent Generalized Zero-Shot Learning [J].

Felix, Rafael ;

Kumar, B. G. Vijay ;

Reid, Ian ;

Carneiro, Gustavo .

COMPUTER VISION - ECCV 2018, PT VI, 2018, 11210 :21-37

[3]

Frome A., 2013, Advances in neural information processing systems

[4] Semantic Autoencoder for Zero-Shot Learning [J].

Kodirov, Elyor ;

Xiang, Tao ;

Gong, Shaogang .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :4447-4456

[5]

Liu S., 2018, ADV NEURAL INFORM PR, P2005

[6] Automated flower classification over a large number of classes [J].

Nilsback, Maria-Elena ;

Zisserman, Andrew .

SIXTH INDIAN CONFERENCE ON COMPUTER VISION, GRAPHICS & IMAGE PROCESSING ICVGIP 2008, 2008, :722-729

[7]

Schonfeld E., 2019, P IEEE C COMP VIS PA, P8247

[8] A Simple Exponential Family Framework for Zero-Shot Learning [J].

Verma, Vinay Kumar ;

Rai, Piyush .

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2017, PT II, 2017, 10535 :792-808

[9]

Wah C., 2014, The Caltech

[10] Feature Generating Networks for Zero-Shot Learning [J].

Xian, Yongqin ;

Lorenz, Tobias ;

Schiele, Bernt ;

Akata, Zeynep .

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, :5542-5551

← 1 2 →