Home /
Research
Showing 409 - 414 / 897
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
ZhendaXie, YutongLin, ZhengZhang....
Published date-11/19/2020
ContrastiveLearning, ObjectDetection, RepresentationLearning, SemanticSegmentation
Contrastive learning methods for unsupervised visual representation learning have reached remarkable levels of transfer performance. We argue that the power of contrastive learning has yet to be fully unleashed, as …
Finding the Homology of Decision Boundaries with Active Learning
WeizhiLi, GautamDasarathy, KarthikeyanNatesanRamamurthy....
Published date-11/19/2020
ActiveLearning, Meta-Learning, ModelSelection, TopologicalDataAnalysis
Accurately and efficiently characterizing the decision boundary of classifiers is important for problems related to model selection and meta-learning. Inspired by topological data analysis, the characterization of decision boundaries using …
FedEval: A Benchmark System with a Comprehensive Evaluation Model for Federated Learning
DiChai, LeyeWang, KaiChen....
Published date-11/19/2020
FederatedLearning
As an innovative solution for privacy-preserving machine learning (ML), federated learning (FL) is attracting much attention from research and industry areas. While new technologies proposed in the past few years …
Unmixing Convolutional Features for Crisp Edge Detection
LinxiHuan, XianweiZheng, NanXue....
Published date-11/19/2020
EdgeDetection
This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly …
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
XingeZhu, HuiZhou, TaiWang....
Published date-11/19/2020
3DSemanticSegmentation, PanopticSegmentation
State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the …
Node Similarity Preserving Graph Convolutional Networks
WeiJin, TylerDerr, YiqiWang....
Published date-11/19/2020
GraphRepresentationLearning, RepresentationLearning, Self-SupervisedLearning
Graph Neural Networks (GNNs) have achieved tremendous success in various real-world applications due to their strong ability in graph representation learning. GNNs explore the graph structure and node features by …