Home /
Research
Showing 133 - 138 / 897
RaP-Net: A Region-wise and Point-wise Weighting Network to Extract Robust Keypoints for Indoor Localization
DongjiangLi, JinyuMiao, XuesongShi....
Published date-12/01/2020
IndoorLocalization, VisualLocalization
Image keypoint extraction is an important step for visual localization. The localization in indoor environment is challenging for that there may be many unreliable features on dynamic or repetitive objects. …
Counting People by Estimating People Flows
WeizheLiu, MathieuSalzmann, PascalFua....
Published date-12/01/2020
ActiveLearning, CrowdCounting, OpticalFlowEstimation
Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in …
Graph Stochastic Neural Networks for Semi-supervised Learning
HaiboWang, ChuanZhou, XinChen....
Published date-12/01/2020
NodeClassification, VariationalInference
Graph Neural Networks (GNNs) have achieved remarkable performance in the task of the semi-supervised node classification. However, most existing models learn a deterministic classification function, which lack sufficient flexibility to …
Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
ZixuanKe, BingLiu, XingchangHuang....
Published date-12/01/2020
ContinualLearning, TransferLearning
Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some …
Robust compressed sensing using generative models
AjilJalal, LiuLiu, AlexandrosG.Dimakis....
Published date-12/01/2020
We consider estimating a high dimensional signal in $\R^n$ using a sublinear number of linear measurements. In analogy to classical compressed sensing, here we assume a generative model as a …
Autoencoders that don't overfit towards the Identity
HaraldSteck....
Published date-12/01/2020
Denoising
Autoencoders (AE) aim to reproduce the output from the input. They may hence tend to overfit towards learning the identity-function between the input and output, i.e., they may predict each …