ED Cubuk, B Zoph, D Mane… - Proceedings of the …, 2019 - openaccess.thecvf.com
Data augmentation is an effective technique for improving the accuracy of modern image classifiers. However, current data augmentation implementations are manually designed. In …
In this paper, we take a closer look at data augmentation for images, and describe a simple procedure called AutoAugment to search for improved data augmentation policies. Our key …
Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in …
S Yun, SJ Oh, B Heo, D Han… - Proceedings of the …, 2021 - openaccess.thecvf.com
ImageNet has been the most popular image classification benchmark, but it is also the one with a significant level of label noise. Recent studies have shown that many samples contain …
Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor …
Many deep learning models, developed in recent years, reach higher ImageNet accuracy than ResNet50, with fewer or comparable FLOPs count. While FLOPs are often seen as a …
Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data …
This paper focuses on model transferability estimation, ie, assessing the performance of pre- trained models on a downstream task without performing fine-tuning. Motivated by the …
L Jiang, D Huang, M Liu… - … conference on machine …, 2020 - proceedings.mlr.press
Performing controlled experiments on noisy data is essential in understanding deep learning across noise levels. Due to the lack of suitable datasets, previous research has only …