Home /
Research
Showing 259 - 264 / 897
Generalization in Reinforcement Learning by Soft Data Augmentation
NicklasHansen, XiaolongWang....
Published date-11/26/2020
DataAugmentation
Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during …
Data-Efficient Classification of Radio Galaxies
AshwinSamudre, LijoGeorge, MahakBansal....
Published date-11/26/2020
Few-ShotLearning, TransferLearning
The continuum emission from radio galaxies can be generally classified into different classes like FRI, FRII, Bent, or Compact. In this paper, we explore the task of radio galaxy classification …
Polarization-driven Semantic Segmentation via Efficient Attention-bridged Fusion
KaiteXiang, KailunYang, KaiweiWang....
Published date-11/26/2020
AutonomousVehicles, SemanticSegmentation
Semantic Segmentation (SS) is promising for outdoor scene perception in safety-critical applications like autonomous vehicles, assisted navigation and so on. However, traditional SS is primarily based on RGB images, which …
NLPStatTest: A Toolkit for Comparing NLP System Performance
HaotianZhu, DeniseMak, JesseGioannini....
Published date-11/26/2020
Statistical significance testing centered on p-values is commonly used to compare NLP system performance, but p-values alone are insufficient because statistical significance differs from practical significance. The latter can be …
TinaFace: Strong but Simple Baseline for Face Detection
YanjiaZhu, HongxiangCai, ShuhanZhang....
Published date-11/26/2020
DataAugmentation, FaceDetection, ObjectDetection
Face detection has received intensive attention in recent years. Many works present lots of special methods for face detection from different perspectives like model architecture, data augmentation, label assignment and …
Omni-GAN: On the Secrets of cGANs and Beyond
PengZhou, LingxiXie, BingbingNi....
Published date-11/26/2020
It has been an important problem to design a proper discriminator for conditional generative adversarial networks (cGANs). In this paper, we investigate two popular choices, the projection-based and classification-based discriminators, …