Home /
Research
Showing 469 - 474 / 897
Learning Efficient GANs using Differentiable Masks and co-Attention Distillation
ShaojieLi, MingbaoLin, YanWang....
Published date-11/17/2020
Generative Adversarial Networks (GANs) have been widely-used in image translation, but their high computational and storage costs impede the deployment on mobile devices. Prevalent methods for CNN compression cannot be …
Close Category Generalization
Yao-YuanYang, CyrusRashtchian, RuslanSalakhutdinov....
Published date-11/17/2020
Few-ShotLearning, Out-of-DistributionDetection, RepresentationLearning
Out-of-distribution generalization is a core challenge in machine learning. We introduce and propose a solution to a new type of out-of-distribution evaluation, which we call close category generalization. This task …
ACSC: Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems
JiaheCui, JianweiNiu, ZhenchaoOuyang....
Published date-11/17/2020
Recently, the rapid development of Solid-State LiDAR (SSL) enables low-cost and efficient obtainment of 3D point clouds from the environment, which has inspired a large quantity of studies and applications. …
Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining
ZijunSun, ChunFan, XiaofeiSun....
Published date-11/17/2020
LanguageModelling, TextClassification
The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, …
Learning outside the Black-Box: The pursuit of interpretable models
JonathanCrabbé, YaoZhang, WilliamZame....
Published date-11/17/2020
Machine Learning has proved its ability to produce accurate models but the deployment of these models outside the machine learning community has been hindered by the difficulties of interpreting these …
Confounding Feature Acquisition for Causal Effect Estimation
ShirlyWang, SeungEunYi, ShalmaliJoshi....
Published date-11/17/2020
CausalInference
Reliable treatment effect estimation from observational data depends on the availability of all confounding information. While much work has targeted treatment effect estimation from observational data, there is relatively little …