Improving Resnet-9 Generalization Trained on Small Datasets

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Awad, Omar Mohamed, Hajimolahoseini, Habib, Lim, Michael, Gosal, Gurpreet, Ahmed, Walid, Liu, Yang, Deng, Gordon
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910965173321728
author Awad, Omar Mohamed
Hajimolahoseini, Habib
Lim, Michael
Gosal, Gurpreet
Ahmed, Walid
Liu, Yang
Deng, Gordon
author_facet Awad, Omar Mohamed
Hajimolahoseini, Habib
Lim, Michael
Gosal, Gurpreet
Ahmed, Walid
Liu, Yang
Deng, Gordon
contents This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training. The challenge is to achieve the highest possible accuracy in an image classification task in less than 10 minutes. The training is done on a small dataset of 5000 images picked randomly from CIFAR-10 dataset. The evaluation is performed by the competition organizers on a secret dataset with 1000 images of the same size. Our approach includes applying a series of technique for improving the generalization of ResNet-9 including: sharpness aware optimization, label smoothing, gradient centralization, input patch whitening as well as metalearning based training. Our experiments show that the ResNet-9 can achieve the accuracy of 88% while trained only on a 10% subset of CIFAR-10 dataset in less than 10 minuets
format Preprint
id arxiv_https___arxiv_org_abs_2309_03965
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Improving Resnet-9 Generalization Trained on Small Datasets
Awad, Omar Mohamed
Hajimolahoseini, Habib
Lim, Michael
Gosal, Gurpreet
Ahmed, Walid
Liu, Yang
Deng, Gordon
Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training. The challenge is to achieve the highest possible accuracy in an image classification task in less than 10 minutes. The training is done on a small dataset of 5000 images picked randomly from CIFAR-10 dataset. The evaluation is performed by the competition organizers on a secret dataset with 1000 images of the same size. Our approach includes applying a series of technique for improving the generalization of ResNet-9 including: sharpness aware optimization, label smoothing, gradient centralization, input patch whitening as well as metalearning based training. Our experiments show that the ResNet-9 can achieve the accuracy of 88% while trained only on a 10% subset of CIFAR-10 dataset in less than 10 minuets
title Improving Resnet-9 Generalization Trained on Small Datasets
topic Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2309.03965