Deep Self-Supervised Representation Learning for Free-Hand Sketch

Xu, Peng, Song, Zeyu, Yin, Qiyue, Song, Yi-Zhe and Wang, Liang (2020) Deep Self-Supervised Representation Learning for Free-Hand Sketch IEEE Transactions on Circuits and Systems for Video Technology.

Full text not available from this repository.

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 that 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 a textual convolution network (TCN) 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.

Item Type:	Article
Divisions :	Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :	Name Email ORCID Xu, Peng Song, Zeyu Yin, Qiyue Song, Yi-Zhe y.song@surrey.ac.uk Wang, Liang
Date :	17 June 2020
DOI :	10.1109/TCSVT.2020.3003048
Copyright Disclaimer :	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords :	Self-supervised; Representation learning; Deep learning; Sketch; Pretext task; Textual convolution network; Convolutional neural network
Depositing User :	Diane Maxfield
Date Deposited :	07 Oct 2020 16:08
Last Modified :	07 Oct 2020 16:08
URI:	http://epubs.surrey.ac.uk/id/eprint/858709

Actions (login required)

View Item

Downloads