Home /
Research
Showing 151 - 156 / 897
Soft Contrastive Learning for Visual Localization
JanineThoma, DandaPaniPaudel, LucV.Gool....
Published date-12/01/2020
ContrastiveLearning, ImageRetrieval, VisualLocalization
Localization by image retrieval is inexpensive and scalable due to simple mapping and matching techniques. Such localization, however, depends upon the quality of image features often obtained using Contrastive learning …
Rethinking Learnable Tree Filter for Generic Feature Transform
LinSong, YanweiLi, ZhengkaiJiang....
Published date-12/01/2020
InstanceSegmentation, ObjectDetection, SemanticSegmentation
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial …
Evaluating Attribution for Graph Neural Networks
BenjaminSanchez-Lengeling, JenniferWei, BrianLee....
Published date-12/01/2020
Interpretability of machine learning models is critical to scientific understanding, AI safety, as well as debugging. Attribution is one approach to interpretability, which highlights input dimensions that are influential to …
VIME: Extending the Success of Self- and Semi-supervised Learning to Tabular Domain
JinsungYoon, YaoZhang, JamesJordon....
Published date-12/01/2020
DataAugmentation, Imputation, Self-SupervisedLearning
Self- and semi-supervised learning frameworks have made significant progress in training machine learning models with limited labeled data in image and language domains. These methods heavily rely on the unique …
Learning to Adapt to Evolving Domains
HongLiu, MingshengLong, JianminWang....
Published date-12/01/2020
DomainAdaptation, Meta-Learning, TransferLearning, UnsupervisedDomainAdaptation
Domain adaptation aims at knowledge transfer from a labeled source domain to an unlabeled target domain. Current domain adaptation methods have made substantial advances in adapting discrete domains. However, this …
Mixed Information Flow for Cross-domain Sequential Recommendations
MuyangMa, PengjieRen, ZhuminChen....
Published date-12/01/2020
TransferLearning
Cross-domain sequential recommendation (CDSR) is the task of predict the next item that the user is most likely to interact with based on past sequential behavior from multiple domains. One …