Gpipe: Efficient training of giant neural networks using pipeline parallelism
Scaling up deep neural network capacity has been known as an effective approach to
improving model quality for several different machine learning tasks. In many cases …
improving model quality for several different machine learning tasks. In many cases …
Autoaugment: Learning augmentation strategies from data
Data augmentation is an effective technique for improving the accuracy of modern image
classifiers. However, current data augmentation implementations are manually designed. In …
classifiers. However, current data augmentation implementations are manually designed. In …
Autoaugment: Learning augmentation policies from data
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 …
procedure called AutoAugment to search for improved data augmentation policies. Our key …
Do better imagenet models transfer better?
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 …
evaluate the relationship between architecture and transfer. An implicit hypothesis in …
Re-labeling imagenet: from single to multi-labels, from global to localized labels
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 …
with a significant level of label noise. Recent studies have shown that many samples contain …
Debiased self-training for semi-supervised learning
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 …
aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor …
Tresnet: High performance gpu-dedicated architecture
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 …
than ResNet50, with fewer or comparable FLOPs count. While FLOPs are often seen as a …
Mixed autoencoder for self-supervised visual representation learning
Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks
via randomly masking image patches and reconstruction. However, effective data …
via randomly masking image patches and reconstruction. However, effective data …
How far pre-trained models are from neural collapse on the target dataset informs their transferability
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 …
trained models on a downstream task without performing fine-tuning. Motivated by the …
Beyond synthetic noise: Deep learning on controlled noisy labels
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 …
learning across noise levels. Due to the lack of suitable datasets, previous research has only …