Home /
Research
Showing 241 - 246 / 904
Towards Fast and Light-Weight Restoration of Dark Images
MohitLamba, AtulBalaji, KaushikMitra....
Published date-11/28/2020
ImageReconstruction
The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et …
Batch Normalization with Enhanced Linear Transformation
YuhuiXu, LingxiXie, CihangXie....
Published date-11/28/2020
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions. In this …
Understanding How BERT Learns to Identify Edits
SamuelStevens, YuSu....
Published date-11/28/2020
Pre-trained transformer language models such as BERT are ubiquitous in NLP research, leading to work on understanding how and why these models work. Attention mechanisms have been proposed as a …
TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
LeiHan, JiechaoXiong, PengSun....
Published date-11/27/2020
ImitationLearning, Starcraft, StarcraftII
StarCraft, one of the most difficult esport games with long-standing history of professional tournaments, has attracted generations of players and fans, and also, intense attentions in artificial intelligence research. Recently, …
Enhancing Diversity in Teacher-Student Networks via Asymmetric branches for Unsupervised Person Re-identification
HaoChen, BenoitLagadec, FrancoisBremond....
Published date-11/27/2020
DomainAdaptation, PersonRe-Identification, UnsupervisedDomainAdaptation, UnsupervisedPersonRe-Identification
The objective of unsupervised person re-identification (Re-ID) is to learn discriminative features without labor-intensive identity annotations. State-of-the-art unsupervised Re-ID methods assign pseudo labels to unlabeled images in the target domain …
Navigating the GAN Parameter Space for Semantic Image Editing
AntonCherepkov, AndreyVoynov, ArtemBabenko....
Published date-11/27/2020
ImageRestoration, Image-to-ImageTranslation
Generative Adversarial Networks (GANs) are currently an indispensable tool for visual editing, being a standard component of image-to-image translation and image restoration pipelines. Furthermore, GANs are especially useful for controllable …