Search Results for author: Xinyu Jin

Found 13 papers, 8 papers with code

Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing

no code implementations6 May 2021 Zhihong Chen, Taiping Yao, Kekai Sheng, Shouhong Ding, Ying Tai, Jilin Li, Feiyue Huang, Xinyu Jin

Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios.

Domain Generalization Face Anti-Spoofing +2

DCANet: Dense Context-Aware Network for Semantic Segmentation

no code implementations6 Apr 2021 Yifu Liu, Chenfeng Xu, Xinyu Jin

As the superiority of context information gradually manifests in advanced semantic segmentation, learning to capture the compact context relationship can help to understand the complex scenes.

Semantic Segmentation

Synthesizing MR Image Contrast Enhancement Using 3D High-resolution ConvNets

1 code implementation4 Apr 2021 Chao Chen, Catalina Raymond, Bill Speier, Xinyu Jin, Timothy F. Cloughesy, Dieter Enzmann, Benjamin M. Ellingson, Corey W. Arnold

To alleviate the data imbalance problem between normal tissues and the tumor regions, we introduce a local loss to improve the contribution of the tumor regions, which leads to better enhancement results on tumors.

Attention-Guided Discriminative Region Localization and Label Distribution Learning for Bone Age Assessment

1 code implementation30 May 2020 Chao Chen, Zhihong Chen, Xinyu Jin, Lanjuan Li, William Speier, Corey W. Arnold

However, training with the global image underutilizes discriminative local information, while providing extra annotations is expensive and subjective.

Age Estimation regression

1D Probabilistic Undersampling Pattern Optimization for MR Image Reconstruction

1 code implementation8 Mar 2020 Shengke Xue, Ruiliang Bai, Xinyu Jin

We propose a 1D probabilistic undersampling layer, to obtain the optimal undersampling pattern and its probability distribution in a differentiable way.

Common Sense Reasoning Image Reconstruction

HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation

1 code implementation27 Dec 2019 Chao Chen, Zhihang Fu, Zhihong Chen, Sheng Jin, Zhaowei Cheng, Xinyu Jin, Xian-Sheng Hua

In particular, our proposed HoMM can perform arbitrary-order moment tensor matching, we show that the first-order HoMM is equivalent to Maximum Mean Discrepancy (MMD) and the second-order HoMM is equivalent to Correlation Alignment (CORAL).

Unsupervised Domain Adaptation

Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation

no code implementations13 Apr 2019 Chao Chen, Zhihang Fu, Zhihong Chen, Zhaowei Cheng, Xinyu Jin, Xian-Sheng Hua

Recent advances in unsupervised domain adaptation mainly focus on learning shared representations by global distribution alignment without considering class information across domains.

Unsupervised Domain Adaptation

Truncated nuclear norm regularization for low-rank tensor completion

1 code implementation7 Jan 2019 Shengke Xue, Wenyuan Qiu, Fan Liu, Xinyu Jin

It is proved that the recently proposed truncated nuclear norm (TNN) can replace the traditional nuclear norm, as an improved approximation to the rank of a matrix.

Parameter Transfer Extreme Learning Machine based on Projective Model

1 code implementation4 Sep 2018 Chao Chen, Boyuan Jiang, Xinyu Jin

Unlike the existing parameter transfer approaches, which incorporate the source model information into the target by regularizing the di erence between the source and target domain parameters, an intuitively appealing projective-model is proposed to bridge the source and target model parameters.

Domain Adaptation

Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

1 code implementation28 Aug 2018 Chao Chen, Zhihong Chen, Boyuan Jiang, Xinyu Jin

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities.

Domain Adaptation

Low-Rank Tensor Completion by Truncated Nuclear Norm Regularization

1 code implementation3 Dec 2017 Shengke Xue, Wenyuan Qiu, Fan Liu, Xinyu Jin

Currently, low-rank tensor completion has gained cumulative attention in recovering incomplete visual data whose partial elements are missing.

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