Home /
Research
Showing 91 - 96 / 897
A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation
RihuanKe, AngelicaAviles-Rivero, SaurabhPandey....
Published date-12/01/2020
SemanticSegmentation, Semi-SupervisedSemanticSegmentation
Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the …
Domain Generalization via Entropy Regularization
ShanshanZhao, MingmingGong, TongliangLiu....
Published date-12/01/2020
DomainGeneralization
Domain generalization aims to learn from multiple source domains a predictive model that can generalize to unseen target domains. One essential problem in domain generalization is to learn discriminative domain-invariant …
Digraph Inception Convolutional Networks
ZekunTong, YuxuanLiang, ChangshengSun....
Published date-12/01/2020
Graph Convolutional Networks (GCNs) have shown promising results in modeling graph-structured data. However, they have difficulty with processing digraphs because of two reasons: 1) transforming directed to undirected graph to …
Barking up the right tree: an approach to search over molecule synthesis DAGs
JohnBradshaw, BrooksPaige, MattJ.Kusner....
Published date-12/01/2020
When designing new molecules with particular properties, it is not only important what to make but crucially how to make it. These instructions form a synthesis directed acyclic graph (DAG), …
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
YongganFu, HaoranYou, YangZhao....
Published date-12/01/2020
Quantization
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due …
Group Contextual Encoding for 3D Point Clouds
XuLiu, ChengtaoLi, JianWang....
Published date-12/01/2020
SceneUnderstanding
Global context is crucial for 3D point cloud scene understanding tasks. In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point …