Denoising in Representation Space via Data-Dependent Regularization for Better Representation

Despite the success of deep learning models, it remains challenging for the over-parameterized model to learn good representation under small-sample-size settings. In this paper, motivated by previous work on out-of-distribution (OoD) generalization, we study the representation learning problem from...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Muyi Chen, Daling Wang, Shi Feng, Yifei Zhang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2023-05-01
coleção:	Mathematics
Assuntos:	deep neural network representation space fully connected layer feature extractor
Acesso em linha:	https://www.mdpi.com/2227-7390/11/10/2327
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!