Quadruplet Augmentation With Attribute and Structure Invariance for Online Continual Learning

Summary

Quadruplet Augmentation (QuadAug) is a method for Online Continual Learning, which learns from streaming data with unknown task boundaries. It targets two requirements, attribute invariance and structure invariance, to overcome the shortcut feature trap and limited plasticity of previous methods. The authors report significant improvements on four sequential datasets and three blurry datasets.