Please use this identifier to cite or link to this item:
Title: Deep self-supervised representation learning for free-hand sketch
Authors: Xu, Peng
Song, Zeyu
Yin, Qiyue
Song, Yi-Zhe
Wang, Liang
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Xu, P., Song, Z., Yin, Q., Song, Y. & Wang, L. (2020). Deep self-supervised representation learning for free-hand sketch. IEEE Transactions On Circuits and Systems for Video Technology, 31(4), 1503-1513.
Journal: IEEE Transactions on Circuits and Systems for Video Technology
Abstract: In this paper, we tackle for the first time, the problem of self-supervised representation learning for free-hand sketches. This importantly addresses a common problem faced by the sketch community - that annotated supervisory data are difficult to obtain. This problem is very challenging in which sketches are highly abstract and subject to different drawing styles, making existing solutions tailored for photos unsuitable. Key for the success of our self-supervised learning paradigm lies with our sketch-specific designs: (i) we propose a set of pretext tasks specifically designed for sketches that mimic different drawing styles, and (ii) we further exploit the use of the textual convolution network (TCN) together with the convolutional neural network (CNN) in a dual-branch architecture for sketch feature learning, as means to accommodate the sequential stroke nature of sketches. We demonstrate the superiority of our sketch-specific designs through two sketch-related applications (retrieval and recognition) on a million-scale sketch dataset, and show that the proposed approach outperforms the state-of-the-art unsupervised representation learning methods, and significantly narrows the performance gap between with supervised representation learning.
ISSN: 1051-8215
DOI: 10.1109/TCSVT.2020.3003048
Schools: School of Computer Science and Engineering 
Rights: © 2020 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

Citations 20

Updated on Nov 25, 2023

Web of ScienceTM
Citations 20

Updated on Oct 29, 2023

Page view(s)

Updated on Nov 30, 2023

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.