Home /

Research

Showing 763 - 768 / 904

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

Authors:  DimitrisFotakis, ThanasisLianeas, GeorgiosPiliouras....
Published date-11/05/2020
Tasks:  DimensionalityReduction

Abstract: We consider a natural model of online preference aggregation, where sets of preferred items $R_1, R_2, \ldots, R_t$ along with a demand for $k_t$ items in each $R_t$, appear online. …
Paper Code

Intriguing Properties of Contrastive Losses

Authors:  TingChen, LalaLi....
Published date-11/05/2020
Tasks:  ContrastiveLearning, DataAugmentation

Abstract: Contrastive loss and its variants have become very popular recently for learning visual representations without supervision. In this work, we first generalize the standard contrastive loss based on cross entropy …
Paper Code

Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks

Authors:  DavidPeer, SebastianStabinger, AntonioRodriguez-Sanchez....
Published date-11/05/2020

Abstract: Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this paper, …
Paper Code

CompressAI: a PyTorch library and evaluation platform for end-to-end compression research

Authors:  JeanBégaint, FabienRacapé, SimonFeltman....
Published date-11/05/2020
Tasks:  ImageCompression, MS-SSIM, SSIM, VideoCompression

Abstract: This paper presents CompressAI, a platform that provides custom operations, layers, models and tools to research, develop and evaluate end-to-end image and video compression codecs. In particular, CompressAI includes pre-trained …
Paper Code

Disentangling Latent Space for Unsupervised Semantic Face Editing

Authors:  KanglinLiu, GaofengCao, FeiZhou....
Published date-11/05/2020
Activation Functions
Adaptive Instance Normalization
Convolution
Convolutions
Dense Connections
Tasks:  ImageGeneration

Abstract: Editing facial images created by StyleGAN is a popular research topic with important applications. Through editing the latent vectors, it is possible to control the facial attributes such as smile, …
Paper Code

Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity

Authors:  TanmayGangwani, JianPeng, YuanZhou....
Published date-11/05/2020

Abstract: Quality-Diversity (QD) is a concept from Neuroevolution with some intriguing applications to Reinforcement Learning. It facilitates learning a population of agents where each member is optimized to simultaneously accumulate high …
Paper Code

Filter by

Categories

Tags