Class Incremental Learning With Deep Contrastive Learning and Attention Distillation
Class incremental learning can solve the issue of catastrophic forgetting when the trained
model is used to learn a new task in which the model may forget part of previous knowledge …
model is used to learn a new task in which the model may forget part of previous knowledge …
A Class Incremental Learning Method with Weight Re-Initialization and Multiple Distillation for Image Classification
Class Incremental Learning is dedicated to solving catastrophic forgetting in which the
performance of previous tasks is severely degraded for adapting to new data in data stream …
performance of previous tasks is severely degraded for adapting to new data in data stream …