Related papers: Consensus-Driven Propagation in Massive Unlabeled …

Medical image segmentation has made significant progress when a large amount of labeled data are available. However, annotating medical image segmentation datasets is expensive due to the requirement of professional skills. Additionally,…

The availability of large-scale data sets is an essential pre-requisite for deep learning based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using…

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this…

Semantic segmentation models based on convolutional neural networks have recently displayed remarkable performance for a multitude of applications. However, these models typically do not generalize well when applied on new domains,…

The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines…

Supervised classification approaches can predict labels for unknown data because of the supervised training process. The success of classification is heavily dependent on the labeled training data. Differently, clustering is effective in…

Owe to the rapid development of deep neural network (DNN) techniques and the emergence of large scale face databases, face recognition has achieved a great success in recent years. During the training process of DNN, the face features and…

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

We address the problem of semi-supervised domain generalization (SSDG), where the distributions of train and test data differ, and only a small amount of labeled data along with a larger amount of unlabeled data are available during…

Face clustering tasks can learn hierarchical semantic information from large-scale data, which has the potential to help facilitate face recognition. However, there are few works on this problem. This paper explores it by proposing a joint…

Utilizing language models (LMs) without internal access is becoming an attractive paradigm in the field of NLP as many cutting-edge LMs are released through APIs and boast a massive scale. The de-facto method in this type of black-box…

Recent years have witnessed a great success of supervised deep learning, where predictive models were trained from a large amount of fully labeled data. However, in practice, labeling such big data can be very costly and may not even be…

The recent rapid and tremendous success of deep convolutional neural networks (CNN) on many challenging computer vision tasks largely derives from the accessibility of the well-annotated ImageNet and PASCAL VOC datasets. Nevertheless,…

Semi-supervised semantic segmentation, which leverages a limited set of labeled images, helps to relieve the heavy annotation burden. While pseudo-labeling strategies yield promising results, there is still room for enhancing the…

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…

We employ the face recognition technology developed in house at face.com to a well accepted benchmark and show that without any tuning we are able to considerably surpass state of the art results. Much of the improvement is concentrated in…

We propose a new approach to interactive full-image semantic segmentation which enables quickly collecting training data for new datasets with previously unseen semantic classes (A demo is available at https://youtu.be/yUk8D5gEX-o). We…

Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come from known or novel classes. The prevailing approach…

The clustering of unlabeled raw images is a daunting task, which has recently been approached with some success by deep learning methods. Here we propose an unsupervised clustering framework, which learns a deep neural network in an…

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…