Home /

Research

Showing 271 - 276 / 897

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs


Authors:  CarlosLassance, LouisBéthune, MyriamBontonou....
Published date-11/25/2020

Abstract: Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) …

BinPlay: A Binary Latent Autoencoder for Generative Replay Continual Learning


Authors:  KamilDeja, PawełWawrzyński, DanielMarczak....
Published date-11/25/2020
Tasks:  ContinualLearning

Abstract: We introduce a binary latent space autoencoder architecture to rehearse training samples for the continual learning of neural networks. The ability to extend the knowledge of a model with new …

Physics-informed neural networks for myocardial perfusion MRI quantification


Authors:  RudolfL.M.vanHerten, AmedeoChiribiri, MarcelBreeuwer....
Published date-11/25/2020

Abstract: Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, …

The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation


Authors:  BjörnBrowatzki, Jörn-PhilippLies, ChristianWallraven....
Published date-11/25/2020
Tasks:  RetinalVesselSegmentation

Abstract: We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of large-scale patches at multiple image-scales during training. Experiments on three …

Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection


Authors:  XiangLi, WenhaiWang, XiaolinHu....
Published date-11/25/2020
Tasks:  DenseObjectDetection, ObjectClassification, ObjectDetection

Abstract: Localization Quality Estimation (LQE) is crucial and popular in the recent advancement of dense object detectors since it can provide accurate ranking scores that benefit the Non-Maximum Suppression processing and …

TLeague: A Framework for Competitive Self-Play based Distributed Multi-Agent Reinforcement Learning


Authors:  PengSun, JiechaoXiong, LeiHan....
Published date-11/25/2020
Tasks:  Dota2, Multi-agentReinforcementLearning, Starcraft, StarcraftII

Abstract: Competitive Self-Play (CSP) based Multi-Agent Reinforcement Learning (MARL) has shown phenomenal breakthroughs recently. Strong AIs are achieved for several benchmarks, including Dota 2, Glory of Kings, Quake III, StarCraft II, …

Filter by

Categories

Tags