Search Results for author: Wen Lu

Found 10 papers, 4 papers with code

MKANet: A Lightweight Network with Sobel Boundary Loss for Efficient Land-cover Classification of Satellite Remote Sensing Imagery

no code implementations28 Jul 2022 Zhiqi Zhang, Wen Lu, Jinshan Cao, Guangqi Xie

Limited by hardware computational resources and memory capacity, most existing studies preprocessed original remote sensing images by down sampling or cropping them into small patches less than 512*512 pixels before sending them to a deep neural network.

Land Cover Classification Semantic Segmentation

Regularized Deep Linear Discriminant Analysis

no code implementations15 May 2021 Wen Lu

As a non-linear extension of the classic Linear Discriminant Analysis(LDA), Deep Linear Discriminant Analysis(DLDA) replaces the original Categorical Cross Entropy(CCE) loss function with eigenvalue-based loss function to make a deep neural network(DNN) able to learn linearly separable hidden representations.

Bergman kernels and equidistribution for sequences of line bundles on Kähler manifolds

no code implementations22 Dec 2020 Dan Coman, Wen Lu, Xiaonan Ma, George Marinescu

Given a sequence of positive Hermitian holomorphic line bundles $(L_p, h_p)$ on a K\"ahler manifold $X$, we establish the asymptotic expansion of the Bergman kernel of the space of global holomorphic sections of $L_p$, under a natural convergence assumption on the sequence of curvatures $c_1(L_p, h_p)$.

Complex Variables Differential Geometry Probability Symplectic Geometry

Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution

1 code implementation28 Sep 2020 Yuanfei Huang, Jie Li, Xinbo Gao, Yanting Hu, Wen Lu

To solve them, we propose a purposeful and interpretable detail-fidelity attention network to progressively process these smoothes and details in divide-and-conquer manner, which is a novel and specific prospect of image super-resolution for the purpose on improving the detail fidelity, instead of blindly designing or employing the deep CNNs architectures for merely feature representation in local receptive fields.

Image Super-Resolution

Distilling with Residual Network for Single Image Super Resolution

no code implementations5 Jul 2019 Xiaopeng Sun, Wen Lu, Rui Wang, Furui Bai

Recently, the deep convolutional neural network (CNN) has made remarkable progress in single image super resolution(SISR).

Image Reconstruction Image Super-Resolution

A Gated Peripheral-Foveal Convolutional Neural Network for Unified Image Aesthetic Prediction

no code implementations19 Dec 2018 Xiaodan Zhang, Xinbo Gao, Wen Lu, Lihuo He

The former aims to mimic the functions of peripheral vision to encode the holistic information and provide the attended regions.

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