Enhancing Few-Shot Image Classification With a Multi-Faceted Self-Supervised and Contrastive Learning Approach

One effective approach for solving few-shot classification is learning deep representations that measure the similarity between query images and a few support images of specific categories. Recent methods overly relied on a single metric, resulting in insufficient interdependence in image feature re...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Ling Hu, Wei Wu
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2024-01-01
Saila:	IEEE Access
Gaiak:	Few-shot learning feature reconstruction self-supervised learning contrastive learning Brownian distance covariance
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/10746489/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!