Rethinking Pseudo-Labeling for Semi-Supervised Facial Expression Recognition With Contrastive Self-Supervised Learning

Self-supervised learning for semi-supervised facial expression recognition aims to avoid the need to collect expensive labeled facial expression data. Existing methods demonstrate an impressive performance boost, but they artificially assume that small labeled facial expression data and large unlabe...

Täydet tiedot

Bibliografiset tiedot

Päätekijät:	Bei Fang, Xian Li, Guangxin Han, Juhou He
Aineistotyyppi:	Artigo
Kieli:	Inglês
Julkaistu:	IEEE 2023-01-01
Sarja:	IEEE Access
Aiheet:	Facial expression recognition semi-supervised learning contrastive self-supervised learning out-of-distribution data
Linkit:	https://ieeexplore.ieee.org/document/10121455/
Tagit:	Lisää tagi Ei tageja, Lisää ensimmäinen tagi!