Abstract: Few-Shot Object Detection (FSOD) aims to detect the objects of novel classes using only a few manually annotated samples. With the few novel class samples, learning the inter-class ...

Abstract: Few-Shot Class-Incremental Learning (FSCIL) faces a huge stability-plasticity challenge due to continuously learning knowledge from new classes with a small number of training samples ...

Not everyone learns the same way—some folks like to see things, others want to talk it out, and some just want to get their ...