Rethinking the Learning Paradigm for Facial Expression Recognition

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Weijie, Li, Bo, Sebe, Nicu, Lepri, Bruno
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917120069074944
author Wang, Weijie
Li, Bo
Sebe, Nicu
Lepri, Bruno
author_facet Wang, Weijie
Li, Bo
Sebe, Nicu
Lepri, Bruno
contents Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation. To simplify the learning paradigm, most previous methods convert ambiguous annotation results into precise one-hot annotations and train FER models in an end-to-end supervised manner. In this paper, we rethink the existing training paradigm and propose that it is better to use weakly supervised strategies to train FER models with original ambiguous annotation.
format Preprint
id arxiv_https___arxiv_org_abs_2209_15402
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Rethinking the Learning Paradigm for Facial Expression Recognition
Wang, Weijie
Li, Bo
Sebe, Nicu
Lepri, Bruno
Computer Vision and Pattern Recognition
Due to the subjective crowdsourcing annotations and the inherent inter-class similarity of facial expressions, the real-world Facial Expression Recognition (FER) datasets usually exhibit ambiguous annotation. To simplify the learning paradigm, most previous methods convert ambiguous annotation results into precise one-hot annotations and train FER models in an end-to-end supervised manner. In this paper, we rethink the existing training paradigm and propose that it is better to use weakly supervised strategies to train FER models with original ambiguous annotation.
title Rethinking the Learning Paradigm for Facial Expression Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2209.15402