To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Several image processing tasks, such as image classification and object detection, have
been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and …

Recently, learning algorithms motivated from sharpness of loss surface as an effective
measure of generalization gap have shown state-of-the-art performances. Nevertheless …

Abstract We present Meta Pseudo Labels, a semi-supervised learning method that achieves
a new state-of-the-art top-1 accuracy of 90.2% on ImageNet, which is 1.6% better than the …

In machine learning, the model is not as complicated as possible. Good generalization
ability means that the model not only performs well on the training data set, but also can …

Regional dropout strategies have been proposed to enhance performance of convolutional
neural network classifiers. They have proved to be effective for guiding the model to attend …

Semi-supervised learning lately has shown much promise in improving deep learning
models when labeled data is scarce. Common among recent approaches is the use of …

Convolutional networks have enjoyed much success in many computer vision applications.
The convolution operation however has a significant weakness in that it only operates on a …

Data augmentation is an essential technique for improving generalization ability of deep
learning models. Recently, AutoAugment\cite {cubuk2018autoaugment} has been proposed …

Label smoothing is an effective regularization tool for deep neural networks (DNNs), which
generates soft labels by applying a weighted average between the uniform distribution and …