Semantic Concentration for Self-Supervised Dense Representations Learning

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from the same instance/category scatter, harming downstream perfor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence. - 1979. - PP(2025) vom: 23. Sept.
1. Verfasser:	Wen, Peisong (VerfasserIn)
Weitere Verfasser:	Xu, Qianqian, Dai, Siran, Cong, Runmin, Huang, Qingming
Format:	Online-Aufsatz
Sprache:	English
Veröffentlicht:	2025
Zugriff auf das übergeordnete Werk:	IEEE transactions on pattern analysis and machine intelligence
Schlagworte:	Journal Article