Login / Signup

Self-supervised Novelty Detection for Continual Learning: A Gradient-Based Approach Boosted by Binary Classification.

Jingbo SunLi YangJiaxin ZhangFrank LiuMahantesh HalappanavarDeliang FanYu Cao
Published in: CSSL (2021)
Keyphrases
  • novelty detection
  • binary classification
  • learning problems
  • multi class
  • learning algorithm
  • learning process
  • prior knowledge
  • unsupervised learning
  • prediction accuracy
  • anomaly detection
  • learning tasks
  • concept drift