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 …

Which samples should be labelled in a large dataset is one of the most important problems
for the training of deep learning. So far, a variety of active sample selection strategies related …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor
attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few …

In this paper, we propose a novel semi-supervised learning (SSL) framework named
BoostMIS that combines adaptive pseudo labeling and informative active annotation to …

Investigating active learning, we focus on the relation between the number of labeled
examples (budget size), and suitable querying strategies. Our theoretical analysis shows a …

In this paper, we study teacher-student learning from the perspective of data initialization
and propose a novel algorithm called Active Teacher for semi-supervised object detection …

Deep active learning aims to reduce the annotation cost for the training of deep models,
which is notoriously data-hungry. Until recently, deep active learning methods were …

Abstract Models can fail in unpredictable ways during deployment due to task ambiguity,
when multiple behaviors are consistent with the provided training data. An example is an …

We study the out-of-distribution generalization of active learning that adaptively selects
samples for annotation in learning the decision boundary of classification. Our empirical …