Topic-aware transformer with hierarchical prompting learning for multi-label image classification

While existing multi-label classification methods primarily focus on capturing label co-occurrence patterns, they often fail to explore the global contextual information and the semantic hierarchy inherent in multi-label datasets, especially in large-scale label spaces, leading to suboptimal feature...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Jiangpeng Wang, Xiao Dai, Benyun Shi, Miao Liu, Yue Peng
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	PeerJ Inc. 2026-01-01
Edice:	PeerJ Computer Science
Témata:	Multi-label learning Topic model Vision transformer Deep learning Hierarchical prompt Auxiliary learning
On-line přístup:	https://peerj.com/articles/cs-3552.pdf
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!