A Comprehensive and Adversarial Approach to Self-Supervised Representation Learning

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE International Conference on Big Data, Big Data 2020
EditorsXintao 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
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages709-717
Number of pages9
ISBN (Electronic)9781728162515
DOIs
Publication statusPublished - 2020 Dec 10
Event8th IEEE International Conference on Big Data, Big Data 2020 - Virtual, Atlanta, United States
Duration: 2020 Dec 102020 Dec 13

Publication series

NameProceedings - 2020 IEEE International Conference on Big Data, Big Data 2020

Conference

Conference8th IEEE International Conference on Big Data, Big Data 2020
CountryUnited States
CityVirtual, Atlanta
Period20-12-1020-12-13

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'A Comprehensive and Adversarial Approach to Self-Supervised Representation Learning'. Together they form a unique fingerprint.

Cite this