A Comprehensive and Adversarial Approach to Self-Supervised Representation Learning

Yi Zhan Xu, Sungwon Han, Sungwon Park, Meeyoung Cha, Cheng Te Li

研究成果: Conference contribution

摘要

Self-supervised representation learning aims to generate effective representations for data instances without the need for manual labels, also known as unsupervised embedding learning, which has been a critical challenge in many existing semi-supervised and supervised learning tasks. This paper proposes a new self-supervised learning approach, called Super-AND, which extends the memory-based pretraining method AND model [13]. Super-AND has its unique set of losses that combines data augmentation in neighborhood discovery for more accurate anchor selection in embedding learning and further presents an adversarial training manner to learn more confident embeddings under the unsupervised setting. Experimental results exhibit that Super-AND outperforms all existing state-of-the-art self-supervised representation learning approaches and achieves an accuracy of 89.2% on the image classification task for CIFAR-10.

原文English
主出版物標題Proceedings - 2020 IEEE International Conference on Big Data, Big Data 2020
編輯Xintao Wu, Chris Jermaine, Li Xiong, Xiaohua Tony Hu, Olivera Kotevska, Siyuan Lu, Weijia Xu, Srinivas Aluru, Chengxiang Zhai, Eyhab Al-Masri, Zhiyuan Chen, Jeff Saltz
發行者Institute of Electrical and Electronics Engineers Inc.
頁面709-717
頁數9
ISBN(電子)9781728162515
DOIs
出版狀態Published - 2020 十二月 10
事件8th IEEE International Conference on Big Data, Big Data 2020 - Virtual, Atlanta, United States
持續時間: 2020 十二月 102020 十二月 13

出版系列

名字Proceedings - 2020 IEEE International Conference on Big Data, Big Data 2020

Conference

Conference8th IEEE International Conference on Big Data, Big Data 2020
國家/地區United States
城市Virtual, Atlanta
期間20-12-1020-12-13

All Science Journal Classification (ASJC) codes

  • 電腦網路與通信
  • 資訊系統
  • 資訊系統與管理
  • 安全、風險、可靠性和品質

指紋

深入研究「A Comprehensive and Adversarial Approach to Self-Supervised Representation Learning」主題。共同形成了獨特的指紋。

引用此