Rotation is frequently listed as a candidate for data augmentation in
co...
Many variants of unsupervised domain adaptation (UDA) problems have been...
Positive-unlabeled learning refers to the process of training a binary
c...
We propose a new optimization framework for aleatoric uncertainty estima...
Semi-supervised learning (SSL) has been proposed to leverage unlabeled d...
Convolutional neural network (CNN) architectures utilize downsampling la...
Deep neural networks (DNNs) trained on large-scale datasets have exhibit...
The extraction of useful deep features is important for many computer vi...
We propose the residual expansion (RE) algorithm: a global (or near-glob...