Few Shot Class Incremental Learning using Vision-Language models

arXiv:2405.01040v1 Announce Type: cross
Abstract: Recent advancements in deep learning have demonstrated remarkable performance comparable to human capabilities across various supervised computer vision tasks. However, the prevalent assumption of having an extensive pool of training data encompassing all classes prior to model training often diverges from real-world scenarios, where limited data availability for novel classes is the norm. The challenge emerges in seamlessly integrating new classes with few samples into the training data, demanding the model to adeptly accommodate these …

abstract arxiv availability capabilities class computer computer vision cs.cl cs.cv data deep learning eess.iv however human incremental language language models performance pool prior tasks training training data type vision vision-language vision-language models world