Pseudo Labels and Soft Multi-Part Corresponding Similarity for Unsupervised Deep Hashing

In recent years, unsupervised deep hashing methods have achieved great success in large-scale image retrieval. However, these approaches still suffer two major problems in real world applications. On the one hand, due to the lack of effective supervision information, hash codes of different categori...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Huiying Li, Yang Li, Xin Xie, Shuai Gao, Dongsheng Mao
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	IEEE 2020-01-01
Edice:	IEEE Access
Témata:	Unsupervised hashing pseudo labels image retrieval multi-part correspondence soft similarity
On-line přístup:	https://ieeexplore.ieee.org/document/9039610/
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!