Search Results for author:
Found 4 papers, 1 papers with code
FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing
Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new and previous classes.
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning
Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting.
FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning
Actual features of new classes and pseudo-features of past classes are fed into a linear classifier which is trained incrementally to discriminate between all classes.
PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning
Mainstream methods need to store two deep models since they integrate new classes using fine-tuning with knowledge distillation from the previous incremental state.
