Search Results for author: Bing Yu

Found 20 papers, 7 papers with code

Multi-scale temporal-frequency attention for music source separation

no code implementations2 Sep 2022 LianWu Chen, Xiguang Zheng, Chen Zhang, Liang Guo, Bing Yu

In recent years, deep neural networks (DNNs) based approaches have achieved the start-of-the-art performance for music source separation (MSS).

Music Source Separation

Solution landscapes of the diblock copolymer-homopolymer model under two-dimensional confinement

no code implementations26 Jan 2021 Zhen Xu, Yucen Han, Jianyuan Yin, Bing Yu, Yasumasa Nishiura, Lei Zhang

We investigate the solution landscapes of the confined diblock copolymer and homopolymer in two-dimensional domain by using the extended Ohta--Kawasaki model.

Soft Condensed Matter Computational Physics

On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks

no code implementations24 May 2019 Bing Yu, Junzhao Zhang, Zhanxing Zhu

Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision.

Image Classification Vocal Bursts Valence Prediction

The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects

no code implementations ICLR 2019 Zhanxing Zhu, Jingfeng Wu, Bing Yu, Lei Wu, Jinwen Ma

Along this line, we theoretically study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics.

Deep-learning based numerical BSDE method for barrier options

no code implementations11 Apr 2019 Bing Yu, Xiaojing Xing, Agus Sudjianto

In this approach, deep learning is used to learn some deterministic functions, which are used in solving the BSDE with terminal conditions.

ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling

no code implementations13 Mar 2019 Bing Yu, Haoteng Yin, Zhanxing Zhu

In this U-shaped network, a paired sampling operation is proposed in spacetime domain accordingly: the pooling (ST-Pool) coarsens the input graph in spatial from its deterministic partition while abstracts multi-resolution temporal dependencies through dilated recurrent skip connections; based on previous settings in the downsampling, the unpooling (ST-Unpool) restores the original structure of spatio-temporal graphs and resumes regular intervals within graph sequences.

Graph Learning Time Series +2

Tangent-Normal Adversarial Regularization for Semi-supervised Learning

1 code implementation CVPR 2019 Bing Yu, Jingfeng Wu, Jinwen Ma, Zhanxing Zhu

The proposed TNAR is composed by two complementary parts, the tangent adversarial regularization (TAR) and the normal adversarial regularization (NAR).

TAR

Pose-Guided Photorealistic Face Rotation

no code implementations CVPR 2018 Yibo Hu, Xiang Wu, Bing Yu, Ran He, Zhenan Sun

Face rotation provides an effective and cheap way for data augmentation and representation learning of face recognition.

Data Augmentation Face Recognition +2

The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects

1 code implementation ICLR 2019 Zhanxing Zhu, Jingfeng Wu, Bing Yu, Lei Wu, Jinwen Ma

Along this line, we study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics.

Load Balanced GANs for Multi-view Face Image Synthesis

no code implementations21 Feb 2018 Jie Cao, Yibo Hu, Bing Yu, Ran He, Zhenan Sun

Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion.

Face Generation

The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems

1 code implementation30 Sep 2017 Weinan E, Bing Yu

We propose a deep learning based method, the Deep Ritz Method, for numerically solving variational problems, particularly the ones that arise from partial differential equations.

Cannot find the paper you are looking for? You can Submit a new open access paper.