Home /

Research

Showing 457 - 462 / 897

Contrastive Registration for Unsupervised Medical Image Segmentation

Authors:  LihaoLiu, AngelicaIAviles-Rivero, Carola-BibianeSchönlieb....
Published date-11/17/2020
Tasks:  ContrastiveLearning, MedicalImageSegmentation, SemanticSegmentation

Abstract: Medical image segmentation is a relevant task as it serves as the first step for several diagnosis processes, thus it is indispensable in clinical usage. Whilst major success has been …
Paper Code

EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Neuroevolution

Authors:  WilliamMcNally, KanavVats, AlexanderWong....
Published date-11/17/2020
Tasks:  KeypointDetection, Multi-PersonPoseEstimation, NeuralArchitectureSearch, PoseEstimation

Abstract: Neural architecture search has proven to be highly effective in the design of computationally efficient, task-specific convolutional neural networks across several areas of computer vision. In 2D human pose estimation, …
Paper Code

Revisiting the Sample Complexity of Sparse Spectrum Approximation of Gaussian Processes

Authors:  QuangMinhHoang, TrongNghiaHoang, HaiPham....
Published date-11/17/2020
Tasks:  GaussianProcesses

Abstract: We introduce a new scalable approximation for Gaussian processes with provable guarantees which hold simultaneously over its entire parameter space. Our approximation is obtained from an improved sample complexity analysis …
Paper Code

Data-Driven Reachability Analysis Using Matrix Zonotopes

Authors:  AmrAlanwar, AnneKoch, FrankAllgöwer....
Published date-11/17/2020

Abstract: In this paper, we propose a data-driven reachability analysis approach for an unknown control system. Reachability analysis is an essential tool for guaranteeing safety properties. However, most current reachability analysis …
Paper Code

Slender Object Detection: Diagnoses and Improvements

Authors:  ZhaoyiWan, YiminChen, SutaoDeng....
Published date-11/17/2020
Tasks:  ObjectDetection

Abstract: In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely slender objects. In real-world scenarios as well as widely-used datasets …
Paper Code

Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning

Authors:  BinLi, YinLi, KevinW.Eliceiri....
Published date-11/17/2020
Tasks:  ContrastiveLearning, ImageClassification, MultipleInstanceLearning, wholeslideimages

Abstract: Whole slide images (WSIs) have large resolutions and usually lack localized annotations. WSI classification can be cast as a multiple instance learning (MIL) problem when only slide-level labels are available. …
Paper Code

Filter by

Categories

Tags