Search Results for author: Xin Ma

Found 15 papers, 2 papers with code

TL-GAN: Improving Traffic Light Recognition via Data Synthesis for Autonomous Driving

no code implementations28 Mar 2022 Danfeng Wang, Xin Ma, Xiaodong Yang

Traffic light recognition, as a critical component of the perception module of self-driving vehicles, plays a vital role in the intelligent transportation systems.

Autonomous Driving Image Generation

Compressing Models with Few Samples: Mimicking then Replacing

no code implementations7 Jan 2022 Huanyu Wang, Junjie Liu, Xin Ma, Yang Yong, Zhenhua Chai, Jianxin Wu

Hence, previous methods optimize the compressed model layer-by-layer and try to make every layer have the same outputs as the corresponding layer in the teacher model, which is cumbersome.

Contrastive Attention Network with Dense Field Estimation for Face Completion

1 code implementation20 Dec 2021 Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Gengyun Jia, Zhenhua Chai, Xiaolin Wei

This multi-scale architecture is beneficial for the decoder to utilize discriminative representations learned from encoders into images.

Face Recognition Facial Inpainting

Separating Boundary Points via Structural Regularization for Very Compact Clusters

no code implementations9 Jun 2021 Xin Ma, Won Hwa Kim

VCC takes advantage of distributions of local relationships of samples near the boundary of clusters, so that they can be properly separated and pulled to cluster centers to form compact clusters.

Deep Clustering

Adaptive Deconvolution-based stereo matching Net for Local Stereo Matching

no code implementations1 Jan 2021 Xin Ma, Zhicheng Zhang, Danfeng Wang, Yu Luo, Hui Yuan

In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy.

Stereo Matching

Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion

no code implementations10 Nov 2020 Yuhe Ding, Xin Ma, Mandi Luo, Aihua Zheng, Ran He

Considering the intuitive artifacts in the existing methods, we propose a contrastive style loss for style rendering to enforce the similarity between the style of rendered photo and the caricature, and simultaneously enhance its discrepancy to the photos.

Caricature Photo-To-Caricature Translation +1

Almost elementariness and fiberwise amenability for étale groupoids

no code implementations2 Nov 2020 Xin Ma, Jianchao Wu

In this paper, we introduce two new approximation properties for \'etale groupoids, almost elementariness and (ubiquitous) fiberwise amenability, inspired by Matui's and Kerr's notions of almost finiteness.

Operator Algebras Dynamical Systems 22A22 (primary) 46L35, 51F30, 37A55, 37B05 (Secondary)

Free-Form Image Inpainting via Contrastive Attention Network

no code implementations29 Oct 2020 Xin Ma, Xiaoqiang Zhou, Huaibo Huang, Zhenhua Chai, Xiaolin Wei, Ran He

It is difficult for encoders to capture such powerful representations under this complex situation.

Image Inpainting

Multi-resolution Graph Neural Network for Identifying Disease-specific Variations in Brain Connectivity

no code implementations3 Dec 2019 Xin Ma, Guorong Wu, Won Hwa Kim

As there is significant interest in understanding the altered interactions between different brain regions that lead to neuro-disorders, it is important to develop data-driven methods that work with a population of graph data for traditional prediction tasks.

Graph Learning

Fast and Incremental Loop Closure Detection Using Proximity Graphs

1 code implementation25 Nov 2019 Shan An, Guangfu Che, Fangru Zhou, Xianglong Liu, Xin Ma, Yu Chen

Visual loop closure detection, which can be considered as an image retrieval task, is an important problem in SLAM (Simultaneous Localization and Mapping) systems.

Image Retrieval Loop Closure Detection +1

Batch Normalization Sampling

no code implementations25 Oct 2018 Zhaodong Chen, Lei Deng, Guoqi Li, Jiawei Sun, Xing Hu, Xin Ma, Yuan Xie

In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration.

Crossbar-aware neural network pruning

no code implementations25 Jul 2018 Ling Liang, Lei Deng, Yueling Zeng, Xing Hu, Yu Ji, Xin Ma, Guoqi Li, Yuan Xie

Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.

Network Pruning

A brief introduction to the Grey Machine Learning

no code implementations4 May 2018 Xin Ma

A short discussion on the priority of this new framework to the existing grey models and LSSVM have also been discussed in this paper.

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