Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer. (arXiv:2208.03767v2 [cs.CV] UPDATED)

In class-incremental learning, the model is expected to learn new classes
continually while maintaining knowledge on previous classes. The challenge here
lies in preserving the model's ability to effectively represent prior classes
in the feature space, while adapting it to represent incoming new classes. We
propose two distillation-based objectives for class incremental learning that
leverage the structure of the feature space to maintain accuracy on previous
classes, as well as enable learning the new classes. In our first objective,
termed …

arxiv clustering cv incremental learning space transfer