Deep semi-supervised learning is a fast-growing field with a range of practical applications.
This paper provides a comprehensive survey on both fundamentals and recent advances in …

Deep neural networks demonstrated their ability to provide remarkable performances on a
wide range of supervised learning tasks (eg, image classification) when trained on extensive …

Semi-supervised learning (SSL) improves model generalization by leveraging massive
unlabeled data to augment limited labeled samples. However, currently, popular SSL …

Pre-training is a dominant paradigm in computer vision. For example, supervised ImageNet
pre-training is commonly used to initialize the backbones of object detection and …

Transfer of pre-trained representations improves sample efficiency and simplifies
hyperparameter tuning when training deep neural networks for vision. We revisit the …

We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet,
which is 2.0% better than the state-of-the-art model that requires 3.5 B weakly labeled …

Semi-supervised learning, ie jointly learning from labeled and unlabeled samples, is an
active research topic due to its key role on relaxing human supervision. In the context of …

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled
data to mitigate the reliance on large labeled datasets. In this work, we unify the current …

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 …

State-of-the-art deep learning models are often trained with a large amount of costly labeled
training data. However, requiring exhaustive manual annotations may degrade the model's …