Search Results for author: Xin Ma

Found 29 papers, 9 papers with code

Inter-object Discriminative Graph Modeling for Indoor Scene Recognition

no code implementations10 Nov 2023 Chuanxin Song, Hanbo Wu, Xin Ma

Leveraging object information within scenes to enhance the distinguishability of feature representations has emerged as a key approach in this domain.

Object Scene Recognition

On the Convergence of Federated Averaging under Partial Participation for Over-parameterized Neural Networks

no code implementations9 Oct 2023 Xin Liu, Wei Li, Dazhi Zhan, Yu Pan, Xin Ma, Yu Ding, Zhisong Pan

Federated learning (FL) is a widely employed distributed paradigm for collaboratively training machine learning models from multiple clients without sharing local data.

Federated Learning

LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models

2 code implementations26 Sep 2023 Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu

To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model.

Text-to-Video Generation Video Generation +1

Semantic-embedded Similarity Prototype for Scene Recognition

no code implementations11 Aug 2023 Chuanxin Song, Hanbo Wu, Xin Ma, Yibin Li

Due to the high inter-class similarity caused by the complex composition and the co-existing objects across scenes, numerous studies have explored object semantic knowledge within scenes to improve scene recognition.

Object object-detection +3

SRRM: Semantic Region Relation Model for Indoor Scene Recognition

1 code implementation15 May 2023 Chuanxin Song, Xin Ma

Despite the remarkable success of convolutional neural networks in various computer vision tasks, recognizing indoor scenes still presents a significant challenge due to their complex composition.

 Ranked #1 on Scene Recognition on MIT Indoor Scenes (10-stage average accuracy metric)

Relation Scene Recognition +1

LEO: Generative Latent Image Animator for Human Video Synthesis

4 code implementations6 May 2023 Yaohui Wang, Xin Ma, Xinyuan Chen, Antitza Dantcheva, Bo Dai, Yu Qiao

Our key idea is to represent motion as a sequence of flow maps in the generation process, which inherently isolate motion from appearance.

Disentanglement Video Editing

Disjoint Masking with Joint Distillation for Efficient Masked Image Modeling

1 code implementation31 Dec 2022 Xin Ma, Chang Liu, Chunyu Xie, Long Ye, Yafeng Deng, Xiangyang Ji

Masked image modeling (MIM) has shown great promise for self-supervised learning (SSL) yet been criticized for learning inefficiency.

object-detection Object Detection +2

Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence

1 code implementation11 Nov 2022 Yang Li, Xin Ma, Raj Sunderraman, Shihao Ji, Suprateek Kundu

We compare the prediction performance for different intelligence measures based on static FC, dynamic FC, and region level time series acquired from the Adolescent Brain Cognitive Development (ABCD) study involving close to 7000 individuals.

feature selection Time Series +1

High-dimensional Measurement Error Models for Lipschitz Loss

no code implementations26 Oct 2022 Xin Ma, Suprateek Kundu

Our estimator is designed to minimize the $L_1$ norm among all estimators belonging to suitable feasible sets, without requiring any knowledge of the noise distribution.

Gender Classification regression +1

FedSSO: A Federated Server-Side Second-Order Optimization Algorithm

no code implementations20 Jun 2022 Xin Ma, Renyi Bao, Jinpeng Jiang, Yang Liu, Arthur Jiang, Jun Yan, Xin Liu, Zhisong Pan

In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL).

Federated Learning

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

1 code implementation CVPR 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

no code implementations20 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.

Clustering 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 +2

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.

Computational Efficiency

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.

BIG-bench Machine Learning

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