Home /

Research

Showing 85 - 90 / 897

Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency


Authors:  FangZhao, ShengcaiLiao, KaihaoZhang....
Published date-12/01/2020
Tasks:  HumanParsing, SemanticParsing, TextureSynthesis

Abstract: This paper proposes a human parsing based texture transfer model via cross-view consistency learning to generate the texture of 3D human body from a single image. We use the semantic …

Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks


Authors:  ZixuanKe, BingLiu, XingchangHuang....
Published date-12/01/2020
Tasks:  ContinualLearning, TransferLearning

Abstract: Existing research on continual learning of a sequence of tasks focused on dealing with catastrophic forgetting, where the tasks are assumed to be dissimilar and have little shared knowledge. Some …

Digraph Inception Convolutional Networks


Authors:  ZekunTong, YuxuanLiang, ChangshengSun....
Published date-12/01/2020

Abstract: Graph Convolutional Networks (GCNs) have shown promising results in modeling graph-structured data. However, they have difficulty with processing digraphs because of two reasons: 1) transforming directed to undirected graph to …

H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks


Authors:  ThomasLimbacher, RobertLegenstein....
Published date-12/01/2020
Tasks:  QuestionAnswering

Abstract: The ability to base current computations on memories from the past is critical for many cognitive tasks such as story understanding. Hebbian-type synaptic plasticity is believed to underlie the retention …

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning​


Authors:  ShreyasFadnavis, JoshuaBatson, EleftheriosGaryfallidis....
Published date-12/01/2020
Tasks:  Denoising, Self-SupervisedLearning

Abstract: Diffusion-weighted magnetic resonance imaging (DWI) is the only non-invasive method for quantifying microstructure and reconstructing white-matter pathways in the living human brain. Fluctuations from multiple sources create significant noise in …

Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design


Authors:  MichaelDennis, NatashaJaques, EugeneVinitsky....
Published date-12/01/2020
Tasks:  TransferLearning

Abstract: A wide range of reinforcement learning (RL) problems --- including robustness, transfer learning, unsupervised RL, and emergent complexity --- require specifying a distribution of tasks or environments in which a …

Filter by

Categories

Tags