Guardado en:
Detalles Bibliográficos
Autor principal: Chen, Hanxiao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2401.03753
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913188707041280
author Chen, Hanxiao
author_facet Chen, Hanxiao
contents This work addresses the problem of semi-supervised image classification tasks with the integration of several effective self-supervised pretext tasks. Different from widely-used consistency regularization within semi-supervised learning, we explored a novel self-supervised semi-supervised learning framework (Color-$S^{4}L$) especially with image colorization proxy task and deeply evaluate performances of various network architectures in such special pipeline. Also, we demonstrated its effectiveness and optimal performance on CIFAR-10, SVHN and CIFAR-100 datasets in comparison to previous supervised and semi-supervised optimal methods.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Color-$S^{4}L$: Self-supervised Semi-supervised Learning with Image Colorization
Chen, Hanxiao
Computer Vision and Pattern Recognition
This work addresses the problem of semi-supervised image classification tasks with the integration of several effective self-supervised pretext tasks. Different from widely-used consistency regularization within semi-supervised learning, we explored a novel self-supervised semi-supervised learning framework (Color-$S^{4}L$) especially with image colorization proxy task and deeply evaluate performances of various network architectures in such special pipeline. Also, we demonstrated its effectiveness and optimal performance on CIFAR-10, SVHN and CIFAR-100 datasets in comparison to previous supervised and semi-supervised optimal methods.
title Color-$S^{4}L$: Self-supervised Semi-supervised Learning with Image Colorization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.03753