Search Results for author: Xinwei Sun

Found 37 papers, 12 papers with code

dS^2LBI: Exploring Structural Sparsity on Deep Network via Differential Inclusion Paths

no code implementations ICML 2020 Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.

Exploring Counterfactual Alignment Loss towards Human-centered AI

no code implementations3 Oct 2023 Mingzhou Liu, Xinwei Sun, Ching-Wen Lee, Yu Qiao, Yizhou Wang

In particular, we utilize the counterfactual generation's ability for causal attribution to introduce a novel loss called the CounterFactual Alignment (CF-Align) loss.

Attribute counterfactual +1

Doubly Robust Proximal Causal Learning for Continuous Treatments

1 code implementation22 Sep 2023 Yong Wu, Yanwei Fu, Shouyan Wang, Xinwei Sun

To address these challenges, we propose a kernel-based DR estimator that can well handle continuous treatments.

Causal Discovery from Subsampled Time Series with Proxy Variables

1 code implementation NeurIPS 2023 Mingzhou Liu, Xinwei Sun, Lingjing Hu, Yizhou Wang

Based on these, we can leverage the proxies to remove the bias induced by the hidden variables and hence achieve identifiability.

Causal Discovery Causal Identification +1

Causal Discovery with Unobserved Variables: A Proxy Variable Approach

1 code implementation9 May 2023 Mingzhou Liu, Xinwei Sun, Yu Qiao, Yizhou Wang

Our observation is that discretizing continuous variables can can lead to serious errors and comprise the power of the proxy.

Causal Discovery Causal Identification

Joint fMRI Decoding and Encoding with Latent Embedding Alignment

no code implementations26 Mar 2023 Xuelin Qian, Yikai Wang, Yanwei Fu, Xinwei Sun, xiangyang xue, Jianfeng Feng

Our Latent Embedding Alignment (LEA) model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.

Image Generation

Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels

1 code implementation2 Jan 2023 Yikai Wang, Yanwei Fu, Xinwei Sun

While Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline, we further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data.

Learning with noisy labels regression

PatchMix Augmentation to Identify Causal Features in Few-shot Learning

no code implementations29 Nov 2022 Chengming Xu, Chen Liu, Xinwei Sun, Siqian Yang, Yabiao Wang, Chengjie Wang, Yanwei Fu

We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features.

Data Augmentation Few-Shot Learning +1

Domain Invariant Model with Graph Convolutional Network for Mammogram Classification

no code implementations21 Apr 2022 Churan Wang, Jing Li, Xinwei Sun, Fandong Zhang, Yizhou Yu, Yizhou Wang

To resolve this problem, we propose a novel framework, namely Domain Invariant Model with Graph Convolutional Network (DIM-GCN), which only exploits invariant disease-related features from multiple domains.

Classification

Recovering Latent Causal Factor for Generalization to Distributional Shifts

1 code implementation NeurIPS 2021 Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu

To avoid such a spurious correlation, we propose \textbf{La}tent \textbf{C}ausal \textbf{I}nvariance \textbf{M}odels (LaCIM) that specifies the underlying causal structure of the data and the source of distributional shifts, guiding us to pursue only causal factor for prediction.

Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition

no code implementations8 Oct 2021 Mingzhou Liu, Xinwei Sun, Fandong Zhang, Yizhou Yu, Yizhou Wang

Finally, to implement this contextual posterior, we introduce a Transformer that takes the object's information as a reference and locates correlated contextual factors.

Emotion Recognition Object +2

Relative Instance Credibility Inference for Learning with Noisy Labels

no code implementations29 Sep 2021 Yikai Wang, Xinwei Sun, Yanwei Fu

Specifically, we re-purpose a sparse linear model with incidental parameters as a unified Relative Instance Credibility Inference (RICI) framework, which will detect and remove outliers in the forward pass of each mini-batch and use the remaining instances to train the network.

Learning with noisy labels

Which Invariance Should We Transfer? A Causal Minimax Learning Approach

1 code implementation5 Jul 2021 Mingzhou Liu, Xiangyu Zheng, Xinwei Sun, Fang Fang, Yizhou Wang

When this condition fails, we surprisingly find with an example that this whole stable set, although can fully exploit stable information, is not the optimal one to transfer.

Domain Generalization

Causal Hidden Markov Model for Time Series Disease Forecasting

no code implementations CVPR 2021 Jing Li, Botong Wu, Xinwei Sun, Yizhou Wang

We propose a causal hidden Markov model to achieve robust prediction of irreversible disease at an early stage, which is safety-critical and vital for medical treatment in early stages.

Time Series Time Series Analysis

Forecasting Irreversible Disease via Progression Learning

no code implementations CVPR 2021 Botong Wu, Sijie Ren, Jing Li, Xinwei Sun, Shiming Li, Yizhou Wang

In order to account for the degree of progression of the disease, we propose a temporal generative model to accurately generate the future image and compare it with the current one to get a residual image.

Disease Prediction

Identifying Invariant Texture Violation for Robust Deepfake Detection

no code implementations19 Dec 2020 Xinwei Sun, Botong Wu, Wei Chen

To learn such an invariance for deepfake detection, our InTeLe introduces an auto-encoder framework with different decoders for pristine and fake images, which are further appended with a shallow classifier in order to separate out the obvious artifact-effect.

DeepFake Detection Face Swapping

Latent Causal Invariant Model

no code implementations4 Nov 2020 Xinwei Sun, Botong Wu, Xiangyu Zheng, Chang Liu, Wei Chen, Tao Qin, Tie-Yan Liu

To avoid spurious correlation, we propose a Latent Causal Invariance Model (LaCIM) which pursues causal prediction.

Disentanglement

Learning Causal Semantic Representation for Out-of-Distribution Prediction

1 code implementation NeurIPS 2021 Chang Liu, Xinwei Sun, Jindong Wang, Haoyue Tang, Tao Li, Tao Qin, Wei Chen, Tie-Yan Liu

Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes the semantic factor with the variation factor due to their domain-specific correlation, while only the semantic factor causes the output.

Domain Adaptation

Bilateral Asymmetry Guided Counterfactual Generating Network for Mammogram Classification

no code implementations30 Sep 2020 Chu-ran Wang, Jing Li, Fandong Zhang, Xinwei Sun, Hao Dong, Yizhou Yu, Yizhou Wang

Mammogram benign or malignant classification with only image-level labels is challenging due to the absence of lesion annotations.

Classification counterfactual +1

Leveraging both Lesion Features and Procedural Bias in Neuroimaging: An Dual-Task Split dynamics of inverse scale space

no code implementations17 Jul 2020 Xinwei Sun, Wenjing Han, Lingjing Hu, Yuan YAO, Yizhou Wang

Specifically, with a variable the splitting term, two estimators are introduced and split apart, i. e. one is for feature selection (the sparse estimator) and the other is for prediction (the dense estimator).

feature selection

TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning

no code implementations ECCV 2020 Xinwei Sun, Yilun Xu, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang

In this paper, we propose a novel information-theoretic approach, namely \textbf{T}otal \textbf{C}orrelation \textbf{G}ain \textbf{M}aximization (TCGM), for semi-supervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i. e., the ground truth posteriors of all modalities.

Disease Prediction Emotion Recognition +1

DessiLBI: Exploring Structural Sparsity of Deep Networks via Differential Inclusion Paths

1 code implementation4 Jul 2020 Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.

iSplit LBI: Individualized Partial Ranking with Ties via Split LBI

1 code implementation NeurIPS 2019 Qianqian Xu, Xinwei Sun, Zhiyong Yang, Xiaochun Cao, Qingming Huang, Yuan YAO

In this paper, instead of learning a global ranking which is agreed with the consensus, we pursue the tie-aware partial ranking from an individualized perspective.

Split LBI for Deep Learning: Structural Sparsity via Differential Inclusion Paths

no code implementations25 Sep 2019 Yanwei Fu, Chen Liu, Donghao Li, Xinwei Sun, Jinshan Zeng, Yuan YAO

Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error.

Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces

1 code implementation23 May 2019 Yanwei Fu, Chen Liu, Donghao Li, Zuyuan Zhong, Xinwei Sun, Jinshan Zeng, Yuan YAO

To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces, which generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously.

$S^{2}$-LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning

no code implementations24 Apr 2019 Yanwei Fu, Donghao Li, Xinwei Sun, Shun Zhang, Yizhou Wang, Yuan YAO

This paper proposes a novel Stochastic Split Linearized Bregman Iteration ($S^{2}$-LBI) algorithm to efficiently train the deep network.

Computational Efficiency Model Selection

A Margin-based MLE for Crowdsourced Partial Ranking

no code implementations29 Jul 2018 Qianqian Xu, Jiechao Xiong, Xinwei Sun, Zhiyong Yang, Xiaochun Cao, Qingming Huang, Yuan YAO

A preference order or ranking aggregated from pairwise comparison data is commonly understood as a strict total order.

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

no code implementations ICML 2018 Bo Zhao, Xinwei Sun, Yanwei Fu, Yuan YAO, Yizhou Wang

To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data.

feature selection Zero-Shot Learning

Zero-shot Learning via Shared-Reconstruction-Graph Pursuit

no code implementations20 Nov 2017 Bo Zhao, Xinwei Sun, Yuan YAO, Yizhou Wang

With the learned SRG, each unseen class prototype (cluster center) in the image feature space can be synthesized by the linear combination of other class prototypes, so that testing instances can be classified based on the distance to these synthesized prototypes.

Clustering Generalized Zero-Shot Learning +1

Split LBI: An Iterative Regularization Path with Structural Sparsity

no code implementations NeurIPS 2016 Chendi Huang, Xinwei Sun, Jiechao Xiong, Yuan YAO

An iterative regularization path with structural sparsity is proposed in this paper based on variable splitting and the Linearized Bregman Iteration, hence called \emph{Split LBI}.

Image Denoising Model Selection

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