Deep Self-Supervised Representation Learning for Free-Hand Sketch
文献类型：期刊论文
| 作者 | Xu, Peng1; Song, Zeyu4; Yin, Qiyue2 ; Song, Yi-Zhe3; Wang, Liang2
|
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2021-04-01 |
| 卷号 | 31期号:4页码:1503-1513 |
| 关键词 | Feature extraction Task analysis Strain Computer architecture Deep learning Deformable models Convolution Self-supervised representation learning deep learning sketch pretext task textual convolution network convolutional neural network |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2020.3003048 |
| 通讯作者 | Xu, Peng(peng.xu@ntu.edu.sg) |
| 英文摘要 | 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. (1) (1) PyTorch code of this work is available at https://github.com/zzz1515151/self-supervised_learning_sketch. |
| 资助项目 | BUPT Excellent Ph.D. ; Student Foundation[CX2017307] ; BUPT-SICE Excellent Graduate Student Innovation Foundation |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000637537200021 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | BUPT Excellent Ph.D. ; Student Foundation ; BUPT-SICE Excellent Graduate Student Innovation Foundation |
| 源URL | [http://ir.ia.ac.cn/handle/173211/44248]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 智能系统与工程 |
| 通讯作者 | Xu, Peng |
| 作者单位 | 1.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 7XH, Surrey, England 4.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xu, Peng,Song, Zeyu,Yin, Qiyue,et al. Deep Self-Supervised Representation Learning for Free-Hand Sketch[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,31(4):1503-1513. |
| APA | Xu, Peng,Song, Zeyu,Yin, Qiyue,Song, Yi-Zhe,&Wang, Liang.(2021).Deep Self-Supervised Representation Learning for Free-Hand Sketch.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,31(4),1503-1513. |
| MLA | Xu, Peng,et al."Deep Self-Supervised Representation Learning for Free-Hand Sketch".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 31.4(2021):1503-1513. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。