Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning. (arXiv:2112.04731v3 [cs.CV] UPDATED)

Class Incremental Learning (CIL) aims at learning a multi-class classifier in
a phase-by-phase manner, in which only data of a subset of the classes are
provided at each phase. Previous works mainly focus on mitigating forgetting in
phases after the initial one. However, we find that improving CIL at its
initial phase is also a promising direction. Specifically, we experimentally
show that directly encouraging CIL Learner at the initial phase to output
similar representations as the model jointly trained on …

arxiv cv incremental learning oracle