Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning

Recent video class-incremental learning usually excessively pursues the accuracy of the newly seen classes and relies on memory sets to mitigate catastrophic forgetting of the old classes. However, limited storage only allows storing a few representative videos. So we propose SNRO, which slightly sh...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-04
Hauptverfasser:	Jiao, Jian, Dai, Yu, Hefei Mei, Qiu, Heqian, Gong, Chuanyang, Tang, Shiyuan, Hao, Xinpeng, Li, Hongliang
Format:	Artikel
Sprache:	eng
Schlagworte:	Consumption Interpolation Learning Semantics Storage
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!