Home /
Research
Showing 205 - 210 / 897
Why model why? Assessing the strengths and limitations of LIME
JürgenDieber, SabrinaKirrane....
Published date-11/30/2020
AutonomousVehicles, DecisionMaking
When it comes to complex machine learning models, commonly referred to as black boxes, understanding the underlying decision making process is crucial for domains such as healthcare and financial services, …
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 …
Automating Artifact Detection in Video Games
ParmidaDavarmanesh, KuanhaoJiang, TingtingOu....
Published date-11/30/2020
In spite of advances in gaming hardware and software, gameplay is often tainted with graphics errors, glitches, and screen artifacts. This proof of concept study presents a machine learning approach …
Systematically Exploring Redundancy Reduction in Summarizing Long Documents
WenXiao, GiuseppeCarenini....
Published date-11/30/2020
Our analysis of large summarization datasets indicates that redundancy is a very serious problem when summarizing long documents. Yet, redundancy reduction has not been thoroughly investigated in neural summarization. In …
Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant
JiWonPark, SebastianWagner-Carena, SimonBirrer....
Published date-11/30/2020
We investigate the use of approximate Bayesian neural networks (BNNs) in modeling hundreds of time-delay gravitational lenses for Hubble constant ($H_0$) determination. Our BNN was trained on synthetic HST-quality images …
DUT: Learning Video Stabilization by Simply Watching Unstable Videos
YufeiXu, JingZhang, StephenJ.Maybank....
Published date-11/30/2020
We propose a Deep Unsupervised Trajectory-based stabilization framework (DUT) in this paper. Traditional stabilizers focus on trajectory-based smoothing, which is controllable but fragile in occluded and textureless cases regarding the …