Home /

Research

Showing 67 - 72 / 897

How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods


Authors:  JeyaVikranthJeyakumar, JosephNoor, Yu-HsiCheng....
Published date-12/01/2020
Tasks:  SentimentAnalysis

Abstract: Explaining the inner workings of deep neural network models have received considerable attention in recent years. Researchers have attempted to provide human parseable explanations justifying why a model performed a …

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, …

Learning efficient task-dependent representations with synaptic plasticity


Authors:  ColinBredenberg, EeroSimoncelli, CristinaSavin....
Published date-12/01/2020

Abstract: Neural populations encode the sensory world imperfectly: their capacity is limited by the number of neurons, availability of metabolic and other biophysical resources, and intrinsic noise. The brain is presumably …

SRG-Net: Unsupervised Segmentation for Terracotta Warrior Point Cloud with 3D Pointwise CNN methods


Authors:  YaoHu, GuohuaGeng, KangLi....
Published date-12/01/2020
Tasks:  Clustering

Abstract: In this paper, we present a seed-region-growing CNN(SRG-Net) for unsupervised part segmentation with 3D point clouds of terracotta warriors. Previous neural network researches in 3D are mainly about supervised classification, …

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 …

Make One-Shot Video Object Segmentation Efficient Again


Authors:  TimMeinhardt, LauraLeal-Taixé....
Published date-12/01/2020
Tasks:  ObjectDetection, SemanticSegmentation, VideoObjectSegmentation, VideoSemanticSegmentation, Youtube-VOS

Abstract: Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is …

Filter by

Categories

Tags