3 accepted papers
Class Incremental Learning (CIL) aims to enable models to continually learn new classes while retaining previously learned knowledge. The principal challenge in CIL is catastrophic forgetting, which prior approaches typically address by distilling knowledge from previous model. However, such way is
Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from a limited set of training samples without forgetting knowledge of previously learned classes. Conventional FSCIL methods typically build a robust feature extractor during the base training session with abundant t…
Arbitrary-oriented objects widely appear in natural scenes, aerial photographs, remote sensing images, etc., and thus arbitrary-oriented object detection has received considerable attention. Many current rotation detectors use plenty of anchors with different orientations to achieve spatial alignmen…