摘要作为一个十余年来快速发展的崭新领域, 深度学习受到了越来越多研究者的关注,
它在特征提取和模型拟合上都有着相较于浅层模型显然的优势. 深度学习善于从原始输入数据中 …

Deep learning, which is a subfield of machine learning, has opened a new era for the
development of neural networks. The auto-encoder is a key component of deep structure …

Can we automatically group images into semantically meaningful clusters when ground-
truth annotations are absent? The task of unsupervised image classification remains an …

We improve the recently-proposed" MixMatch" semi-supervised learning algorithm by
introducing two new techniques: distribution alignment and augmentation anchoring …

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 …

This paper studies the unsupervised embedding learning problem, which requires an
effective similarity measurement between samples in low-dimensional embedding space …

We present a novel clustering objective that learns a neural network classifier from scratch,
given only unlabelled data samples. The model discovers clusters that accurately match …

We propose a new regularization method based on virtual adversarial loss: a new measure
of local smoothness of the conditional label distribution given input. Virtual adversarial loss …

We present a variety of new architectural features and training procedures that we apply to
the generative adversarial networks (GANs) framework. Using our new techniques, we …

Image clustering is a crucial but challenging task in machine learning and computer vision.
Existing methods often ignore the combination between feature learning and clustering. To …