Cuepervision: self-supervised learning for continuous domain adaptation without catastrophic forgetting

作者：

Highlights：

• Self-supervised continuous domain adaptation by pseudo-labels.

• Cue-based bypassing of catastrophic forgetting during continuous domain adaptation.

• Seamless deployment of models along continuous domain shifts.

摘要

•Self-supervised continuous domain adaptation by pseudo-labels.•Cue-based bypassing of catastrophic forgetting during continuous domain adaptation.•Seamless deployment of models along continuous domain shifts.

论文关键词：Domain adaptation,Self-supervised learning,Unsupervised learning,Continuous transfer learning,Catastrophic forgetting,MNIST dataset

论文评审过程：Received 10 August 2020, Revised 10 November 2020, Accepted 25 November 2020, Available online 5 December 2020, Version of Record 25 December 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2020.104079