Home /

Research

Showing 127 - 132 / 897

Efficient Low Rank Gaussian Variational Inference for Neural Networks


Authors:  MarcinTomczak, SiddharthSwaroop, RichardTurner....
Published date-12/01/2020
Tasks:  VariationalInference

Abstract: Bayesian neural networks are enjoying a renaissance driven in part by recent advances in variational inference (VI). The most common form of VI employs a fully factorized or mean-field distribution, …

On Statistical Analysis of MOEAs with Multiple Performance Indicators


Authors:  HaoWang, CarlosIgncioHernándezCastellanos, TomeEftimov....
Published date-12/01/2020

Abstract: Assessing the empirical performance of Multi-Objective Evolutionary Algorithms (MOEAs) is vital when we extensively test a set of MOEAs and aim to determine a proper ranking thereof. Multiple performance indicators, …

Unsupervised Anomaly Detection From Semantic Similarity Scores


Authors:  NimaRafiee, RahilGholamipoor, MarkusKollmann....
Published date-12/01/2020
Tasks:  AnomalyDetection, Out-of-DistributionDetection, SemanticSimilarity, SemanticTextualSimilarity, UnsupervisedAnomalyDetection

Abstract: In this paper, we present SemSAD, a simple and generic framework for detecting examples that lie out-of-distribution (OOD) for a given training set. The approach is based on learning a …

Baxter Permutation Process


Authors:  MasahiroNakano, AkisatoKimura, TakeshiYamada....
Published date-12/01/2020
Tasks:  BayesianInference

Abstract: In this paper, a Bayesian nonparametric (BNP) model for Baxter permutations (BPs), termed BP process (BPP) is proposed and applied to relational data analysis. The BPs are a well-studied class …

The Dilemma of TriHard Loss and an Element-Weighted TriHard Loss for Person Re-Identification


Authors:  YihaoLv, YouzhiGu, LiuXinggao....
Published date-12/01/2020
Tasks:  PersonRe-Identification

Abstract: Triplet loss with batch hard mining (TriHard loss) is an important variation of triplet loss inspired by the idea that hard triplets improve the performance of metric leaning networks. However, …

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning​


Authors:  ShreyasFadnavis, JoshuaBatson, EleftheriosGaryfallidis....
Published date-12/01/2020
Tasks:  Denoising, Self-SupervisedLearning

Abstract: Diffusion-weighted magnetic resonance imaging (DWI) is the only non-invasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant noise in …

Filter by

Categories

Tags