OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning

arXiv:2403.18550v1 Announce Type: new
Abstract: Few-Shot Class-Incremental Learning (FSCIL) introduces a paradigm in which the problem space expands with limited data. FSCIL methods inherently face the challenge of catastrophic forgetting as data arrives incrementally, making models susceptible to overwriting previously acquired knowledge. Moreover, given the scarcity of labeled samples available at any given time, models may be prone to overfitting and find it challenging to strike a balance between extensive pretraining and the limited incremental data. To address these challenges, …

arxiv class contrast cs.cv few-shot incremental type via