Abstract: Few-shot Class Incremental Learning (FSCIL) presents a challenging yet realistic scenario, which requires the model to continually learn new classes with limited labeled data (i.e., ...
Abstract: Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn novel classes with limited samples after pre-training on a set of base classes. To avoid catastrophic forgetting and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results