Search Results for author: Ying Sun

Found 46 papers, 11 papers with code

TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression

no code implementations1 Apr 2024 Zelin He, Ying Sun, Jingyuan Liu, Runze Li

Nonasymptotic bound is provided for the estimation error of the target model, showing the robustness of the proposed method to covariate shifts.

regression Transfer Learning

The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity

no code implementations23 Mar 2024 Tongle Wu, Ying Sun

Specifically, for $\mu$-strongly convex and $L$-smooth loss functions, we proved that local DGT achieves communication complexity $\tilde{\mathcal{O}} \Big(\frac{L}{\mu K} + \frac{\delta}{\mu (1 - \rho)} + \frac{\rho }{(1 - \rho)^2} \cdot \frac{L+ \delta}{\mu}\Big)$, where $\rho$ measures the network connectivity and $\delta$ measures the second-order heterogeneity of the local loss.

AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression

no code implementations20 Mar 2024 Zelin He, Ying Sun, Jingyuan Liu, Runze Li

We consider the transfer learning problem in the high dimensional setting, where the feature dimension is larger than the sample size.

Transfer Learning

SGD with Partial Hessian for Deep Neural Networks Optimization

1 code implementation5 Mar 2024 Ying Sun, Hongwei Yong, Lei Zhang

Compared with first-order optimizers, it adopts a certain amount of information from the Hessian matrix to assist optimization, while compared with the existing second-order optimizers, it keeps the good generalization performance of first-order optimizers.

Image Classification Second-order methods

Team I2R-VI-FF Technical Report on EPIC-KITCHENS VISOR Hand Object Segmentation Challenge 2023

no code implementations31 Oct 2023 Fen Fang, Yi Cheng, Ying Sun, Qianli Xu

In this report, we present our approach to the EPIC-KITCHENS VISOR Hand Object Segmentation Challenge, which focuses on the estimation of the relation between the hands and the objects given a single frame as input.

Hand Segmentation Object +2

Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution

no code implementations27 Sep 2023 Ying Sun, HengShu Zhu, Hui Xiong

Self-interpreting neural networks have garnered significant interest in research.

Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering

no code implementations25 Jul 2023 Yi Cheng, Hehe Fan, Dongyun Lin, Ying Sun, Mohan Kankanhalli, Joo-Hwee Lim

The main challenge in video question answering (VideoQA) is to capture and understand the complex spatial and temporal relations between objects based on given questions.

graph construction Question Answering +2

Bivariate DeepKriging for Large-scale Spatial Interpolation of Wind Fields

no code implementations16 Jul 2023 Pratik Nag, Ying Sun, Brian J Reich

Large-scale spatial interpolation or downscaling of bivariate wind fields having velocity in two dimensions is a challenging task because wind data tend to be non-Gaussian with high spatial variability and heterogeneity.

Computational Efficiency Gaussian Processes +2

A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023

no code implementations13 Jul 2023 Yi Cheng, Ziwei Xu, Fen Fang, Dongyun Lin, Hehe Fan, Yongkang Wong, Ying Sun, Mohan Kankanhalli

Our research focuses on the innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models (LLMs) to generate the logic rules for the adaptation to unseen action labels.

Action Recognition Unsupervised Domain Adaptation

A Comprehensive Survey of Artificial Intelligence Techniques for Talent Analytics

no code implementations3 Jul 2023 Chuan Qin, Le Zhang, Rui Zha, Dazhong Shen, Qi Zhang, Ying Sun, Chen Zhu, HengShu Zhu, Hui Xiong

To this end, we present an up-to-date and comprehensive survey on AI technologies used for talent analytics in the field of human resource management.

Decision Making Management

Training-free Object Counting with Prompts

1 code implementation30 Jun 2023 Zenglin Shi, Ying Sun, Mengmi Zhang

However, the vanilla mask generation method of SAM lacks class-specific information in the masks, resulting in inferior counting accuracy.

Object Segmentation +2

Spatio-temporal DeepKriging for Interpolation and Probabilistic Forecasting

no code implementations20 Jun 2023 Pratik Nag, Ying Sun, Brian J Reich

Gaussian processes (GP) and Kriging are widely used in traditional spatio-temporal mod-elling and prediction.

Gaussian Processes Imputation

Meta Compositional Referring Expression Segmentation

no code implementations CVPR 2023 Li Xu, Mark He Huang, Xindi Shang, Zehuan Yuan, Ying Sun, Jun Liu

Then, following a novel meta optimization scheme to optimize the model to obtain good testing performance on the virtual testing sets after training on the virtual training set, our framework can effectively drive the model to better capture semantics and visual representations of individual concepts, and thus obtain robust generalization performance even when handling novel compositions.

Meta-Learning Referring Expression +2

Domain-knowledge Inspired Pseudo Supervision (DIPS) for Unsupervised Image-to-Image Translation Models to Support Cross-Domain Classification

2 code implementations18 Mar 2023 Firas Al-Hindawi, Md Mahfuzur Rahman Siddiquee, Teresa Wu, Han Hu, Ying Sun

Cross-domain classification frameworks were developed to handle this data domain shift problem by utilizing unsupervised image-to-image translation models to translate an input image from the unlabeled domain to the labeled domain.

domain classification Translation +1

Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022

no code implementations29 Jan 2023 Yi Cheng, Dongyun Lin, Fen Fang, Hao Xuan Woon, Qianli Xu, Ying Sun

In this report, we present the technical details of our submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation (UDA) Challenge for Action Recognition 2022.

Action Recognition Unsupervised Domain Adaptation

A General Regret Bound of Preconditioned Gradient Method for DNN Training

1 code implementation CVPR 2023 Hongwei Yong, Ying Sun, Lei Zhang

Though the full-matrix preconditioned gradient methods theoretically have a lower regret bound, they are impractical for use to train DNNs because of the high complexity.

Image Classification object-detection +1

Classifications of Single-input Lower Triangular Forms

no code implementations15 Aug 2022 Duan Zhang, Ying Sun

It is verified that the type that a given lower triangular form belongs to is invariant under any lower triangular coordinate transformation.

Vocal Bursts Type Prediction

Monitoring Vegetation From Space at Extremely Fine Resolutions via Coarsely-Supervised Smooth U-Net

no code implementations16 Jul 2022 Joshua Fan, Di Chen, Jiaming Wen, Ying Sun, Carla P. Gomes

This poses a challenging coarsely-supervised regression (or downscaling) task; at training time, we only have SIF labels at a coarse resolution (3km), but we want to predict SIF at much finer spatial resolutions (e. g. 30m, a 100x increase).

Tackling Data Heterogeneity: A New Unified Framework for Decentralized SGD with Sample-induced Topology

no code implementations8 Jul 2022 Yan Huang, Ying Sun, Zehan Zhu, Changzhi Yan, Jinming Xu

We develop a general framework unifying several gradient-based stochastic optimization methods for empirical risk minimization problems both in centralized and distributed scenarios.

Stochastic Optimization

Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021

no code implementations3 Jun 2022 Yi Cheng, Fen Fang, Ying Sun

Based on an existing method for video domain adaptation, i. e., TA3N, we propose to learn hand-centric features by leveraging the hand bounding box information for UDA on fine-grained action recognition.

Fine-grained Action Recognition Optical Flow Estimation +1

TAILOR: Teaching with Active and Incremental Learning for Object Registration

no code implementations24 May 2022 Qianli Xu, Nicolas Gauthier, Wenyu Liang, Fen Fang, Hui Li Tan, Ying Sun, Yan Wu, Liyuan Li, Joo-Hwee Lim

When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor-intensive.

Incremental Learning Object

A Comprehensive 3-D Framework for Automatic Quantification of Late Gadolinium Enhanced Cardiac Magnetic Resonance Images

no code implementations21 May 2022 Dong Wei, Ying Sun, Sim-Heng Ong, Ping Chai, Lynette L Teo, Adrian F Low

To achieve accurate quantification, LGE CMR images need to be processed in two steps: segmentation of the myocardium followed by classification of infarcts within the segmented myocardium.


Myocardial Segmentation of Late Gadolinium Enhanced MR Images by Propagation of Contours from Cine MR Images

no code implementations21 May 2022 Dong Wei, Ying Sun, Ping Chai, Adrian Low, Sim Heng Ong

Automatic segmentation of myocardium in Late Gadolinium Enhanced (LGE) Cardiac MR (CMR) images is often difficult due to the intensity heterogeneity resulting from accumulation of contrast agent in infarcted areas.


Bone marrow sparing for cervical cancer radiotherapy on multimodality medical images

no code implementations20 Apr 2022 Yuening Wang, Ying Sun, Jie Yuan, Kexin Gan, Hanzi Xu, Han Gao, Xiuming Zhang

Experiments on patient dataset reveal that our proposed method can enhance the multimodal image registration accuracy and efficiency for medical practitioners in sparing BM of cervical cancer radiotherapy.

Image Registration Point cloud reconstruction

High-Dimensional Inference over Networks: Linear Convergence and Statistical Guarantees

no code implementations21 Jan 2022 Ying Sun, Marie Maros, Gesualdo Scutari, Guang Cheng

Our theory shows that, under standard notions of restricted strong convexity and smoothness of the loss functions, suitable conditions on the network connectivity and algorithm tuning, the distributed algorithm converges globally at a {\it linear} rate to an estimate that is within the centralized {\it statistical precision} of the model, $O(s\log d/N)$.

Vocal Bursts Intensity Prediction

Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation

1 code implementation NeurIPS 2021 Ying Sun, HengShu Zhu, Chuan Qin, Fuzhen Zhuang, Qing He, Hui Xiong

To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN).

Decision Making

FashionSearchNet-v2: Learning Attribute Representations with Localization for Image Retrieval with Attribute Manipulation

no code implementations28 Nov 2021 Kenan E. Ak, Joo Hwee Lim, Ying Sun, Jo Yew Tham, Ashraf A. Kassim

A key challenge in e-commerce is that images have multiple attributes where users would like to manipulate and it is important to estimate discriminative feature representations for each of these attributes.

Attribute Image Retrieval +1

Distributed Sparse Regression via Penalization

no code implementations12 Nov 2021 Yao Ji, Gesualdo Scutari, Ying Sun, Harsha Honnappa

First, we establish statistical consistency of the estimator: under a suitable choice of the penalty parameter, the optimal solution of the penalized problem achieves near optimal minimax rate $\mathcal{O}(s \log d/N)$ in $\ell_2$-loss, where $s$ is the sparsity value, $d$ is the ambient dimension, and $N$ is the total sample size in the network -- this matches centralized sample rates.


Hybrid Local SGD for Federated Learning with Heterogeneous Communications

no code implementations ICLR 2022 Yuanxiong Guo, Ying Sun, Rui Hu, Yanmin Gong

Communication is a key bottleneck in federated learning where a large number of edge devices collaboratively learn a model under the orchestration of a central server without sharing their own training data.

Federated Learning

Using BART to Perform Pareto Optimization and Quantify its Uncertainties

no code implementations4 Jan 2021 Akira Horiguchi, Thomas J. Santner, Ying Sun, Matthew T. Pratola

This article proposes Pareto Front (PF) and Pareto Set (PS) estimation methods using Bayesian Additive Regression Trees (BART), which is a non-parametric model whose assumptions are typically less restrictive than popular alternatives, such as Gaussian Processes (GPs).

Gaussian Processes Multiobjective Optimization

DeepKriging: Spatially Dependent Deep Neural Networks for Spatial Prediction

1 code implementation23 Jul 2020 Wanfang Chen, Yuxiao Li, Brian J. Reich, Ying Sun

Kriging provides the best linear unbiased predictor using covariance functions and is often associated with Gaussian processes.

Gaussian Processes General Classification

Accelerated Primal-Dual Algorithms for Distributed Smooth Convex Optimization over Networks

1 code implementation23 Oct 2019 Jinming Xu, Ye Tian, Ying Sun, Gesualdo Scutari

This paper proposes a novel family of primal-dual-based distributed algorithms for smooth, convex, multi-agent optimization over networks that uses only gradient information and gossip communications.

Distributed Optimization

A Semi-Parametric Estimation Method for the Quantile Spectrum with an Application to Earthquake Classification Using Convolutional Neural Network

1 code implementation16 Oct 2019 Tianbo Chen, Ying Sun, Ta-Hsin Li

At each quantile level, we approximate the quantile spectrum by a function in the form of an ordinary AR spectrum.

Methodology Applications

6D Pose Estimation with Correlation Fusion

no code implementations24 Sep 2019 Yi Cheng, Hongyuan Zhu, Ying Sun, Cihan Acar, Wei Jing, Yan Wu, Liyuan Li, Cheston Tan, Joo-Hwee Lim

To our best knowledge, this is the first work to explore effective intra- and inter-modality fusion in 6D pose estimation.

6D Pose Estimation 6D Pose Estimation using RGB

Decentralized Dictionary Learning Over Time-Varying Digraphs

no code implementations17 Aug 2018 Amir Daneshmand, Ying Sun, Gesualdo Scutari, Francisco Facchinei, Brian M. Sadler

This paper studies Dictionary Learning problems wherein the learning task is distributed over a multi-agent network, modeled as a time-varying directed graph.

Dictionary Learning

Likelihood Approximation With Hierarchical Matrices For Large Spatial Datasets

2 code implementations8 Sep 2017 Alexander Litvinenko, Ying Sun, Marc G. Genton, David Keyes

We use available measurements to estimate the unknown parameters (variance, smoothness parameter, and covariance length) of a covariance function by maximizing the joint Gaussian log-likelihood function.

Computation 62F99, 62P12, 62M30 G.3; G.4; J.2

Orthogonal Sparse PCA and Covariance Estimation via Procrustes Reformulation

no code implementations12 Feb 2016 Konstantinos Benidis, Ying Sun, Prabhu Babu, Daniel P. Palomar

In addition, we propose a method to improve the covariance estimation problem when its underlying eigenvectors are known to be sparse.

Robust Estimation of Structured Covariance Matrix for Heavy-Tailed Elliptical Distributions

no code implementations17 Jun 2015 Ying Sun, Prabhu Babu, Daniel P. Palomar

This paper considers the problem of robustly estimating a structured covariance matrix with an elliptical underlying distribution with known mean.

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