Home /
Research
Showing 217 - 222 / 897
Towards constraining warm dark matter with stellar streams through neural simulation-based inference
JoeriHermans, NilanjanBanik, ChristophWeniger....
Published date-11/30/2020
BayesianInference
A statistical analysis of the observed perturbations in the density of stellar streams can in principle set stringent contraints on the mass function of dark matter subhaloes, which in turn …
UWB at SemEval-2020 Task 1: Lexical Semantic Change Detection
OndřejPražák, PavelPřibáň, StephenTaylor....
Published date-11/30/2020
In this paper, we describe our method for the detection of lexical semantic change, i.e., word sense changes over time. We examine semantic differences between specific words in two corpora, …
Inter-layer Transition in Neural Architecture Search
BentengMa, JingZhang, YongXia....
Published date-11/30/2020
NeuralArchitectureSearch
Differential Neural Architecture Search (NAS) methods represent the network architecture as a repetitive proxy directed acyclic graph (DAG) and optimize the network weights and architecture weights alternatively in a differential …
Heuristic Domain Adaptation
ShuhaoCui, XuanJin, ShuhuiWang....
Published date-11/30/2020
DomainAdaptation
In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem. Existing methods apply different kinds of priors or directly minimize the domain discrepancy …
Multi-scale Adaptive Task Attention Network for Few-Shot Learning
HaoxingChen, HuaxiongLi, YaohuiLi....
Published date-11/30/2020
Few-ShotLearning, MetricLearning
The goal of few-shot learning is to classify unseen categories with few labeled samples. Recently, the low-level information metric-learning based methods have achieved satisfying performance, since local representations (LRs) are …
Intrinsic Decomposition of Document Images In-the-Wild
SagnikDas, HassanAhmedSial, KeMa....
Published date-11/29/2020
IntrinsicImageDecomposition, OpticalCharacterRecognition, ShadowRemoval
Automatic document content processing is affected by artifacts caused by the shape of the paper, non-uniform and diverse color of lighting conditions. Fully-supervised methods on real data are impossible due …