Search Results for author: Xi Peng

Found 79 papers, 29 papers with code

Provable Dynamic Fusion for Low-Quality Multimodal Data

no code implementations3 Jun 2023 Qingyang Zhang, Haitao Wu, Changqing Zhang, QinGhua Hu, Huazhu Fu, Joey Tianyi Zhou, Xi Peng

The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction.

dugMatting: Decomposed-Uncertainty-Guided Matting

1 code implementation2 Jun 2023 Jiawei Wu, Changqing Zhang, Zuoyong Li, Huazhu Fu, Xi Peng, Joey Tianyi Zhou

Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing.

Image Matting Video Editing

Semantic Invariant Multi-view Clustering with Fully Incomplete Information

no code implementations22 May 2023 Pengxin Zeng, Mouxing Yang, Yiding Lu, Changqing Zhang, Peng Hu, Xi Peng

To address this problem, we present a novel framework called SeMantic Invariance LEarning (SMILE) for multi-view clustering with incomplete information that does not require any paired samples.


Deep Multiview Clustering by Contrasting Cluster Assignments

no code implementations21 Apr 2023 Jie Chen, Hua Mao, Wai Lok Woo, Xi Peng

Then, a cluster-level CVCL strategy is presented to explore consistent semantic label information among the multiple views in the fine-tuning stage.

Contrastive Learning Multiview Clustering

GLOW: Global Layout Aware Attacks on Object Detection

no code implementations27 Feb 2023 Buyu Liu, BaoJun, Jianping Fan, Xi Peng, Kui Ren, Jun Yu

More desired attacks, to this end, should be able to fool defenses with such consistency checks.

object-detection Object Detection

Incomplete Multi-view Clustering via Prototype-based Imputation

no code implementations26 Jan 2023 Haobin Li, Yunfan Li, Mouxing Yang, Peng Hu, Dezhong Peng, Xi Peng

Thanks to our dual-stream model, both cluster- and view-specific information could be captured, and thus the instance commonality and view versatility could be preserved to facilitate IMvC.

Contrastive Learning Imputation +1

Rethinking Image Super Resolution From Long-Tailed Distribution Learning Perspective

no code implementations CVPR 2023 Yuanbiao Gou, Peng Hu, Jiancheng Lv, Hongyuan Zhu, Xi Peng

Existing studies have empirically observed that the resolution of the low-frequency region is easier to enhance than that of the high-frequency one.

Image Super-Resolution

Comprehensive and Delicate: An Efficient Transformer for Image Restoration

no code implementations CVPR 2023 Haiyu Zhao, Yuanbiao Gou, Boyun Li, Dezhong Peng, Jiancheng Lv, Xi Peng

Vision Transformers have shown promising performance in image restoration, which usually conduct window- or channel-based attention to avoid intensive computations.

Image Restoration Superpixels

Relationship Quantification of Image Degradations

no code implementations8 Dec 2022 Wenxin Wang, Boyun Li, Yuanbiao Gou, Peng Hu, Xi Peng

In this paper, we study two challenging but less-touched problems in image restoration, namely, i) how to quantify the relationship between different image degradations and ii) how to improve the performance on a specific degradation using the quantified relationship.

Denoising Image Dehazing +2

Graph Matching with Bi-level Noisy Correspondence

no code implementations8 Dec 2022 Yijie Lin, Mouxing Yang, Jun Yu, Peng Hu, Changqing Zhang, Xi Peng

In this paper, we study a novel and widely existing problem in graph matching (GM), namely, Bi-level Noisy Correspondence (BNC), which refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC).

Contrastive Learning Graph Matching

Twin Contrastive Learning for Online Clustering

2 code implementations21 Oct 2022 Yunfan Li, Mouxing Yang, Dezhong Peng, Taihao Li, Jiantao Huang, Xi Peng

Specifically, we find that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively.

Contrastive Learning Deep Clustering +2

Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric

no code implementations CVPR 2023 Pengxin Zeng, Yunfan Li, Peng Hu, Dezhong Peng, Jiancheng Lv, Xi Peng

Fair clustering aims to divide data into distinct clusters while preventing sensitive attributes (\textit{e. g.}, gender, race, RNA sequencing technique) from dominating the clustering.


Robust Domain Adaptation for Machine Reading Comprehension

no code implementations23 Sep 2022 Liang Jiang, Zhenyu Huang, Jia Liu, Zujie Wen, Xi Peng

Such a process will inevitably introduce mismatched pairs (i. e., noisy correspondence) due to i) the unavailable QA pairs in target documents, and ii) the domain shift during applying the QA construction model to the target domain.

Domain Adaptation Machine Reading Comprehension

FALCON: Faithful Neural Semantic Entailment over ALC Ontologies

1 code implementation16 Aug 2022 Zhenwei Tang, Tilman Hinnerichs, Xi Peng, Xiangliang Zhang, Robert Hoehndorf

Neural networks using distributed representations can benefit from computing semantic entailments because they enable finding contradictions, implied knowledge, or computing plans on how to achieve distant goals.

TAR: Neural Logical Reasoning across TBox and ABox

no code implementations29 May 2022 Zhenwei Tang, Shichao Pei, Xi Peng, Fuzhen Zhuang, Xiangliang Zhang, Robert Hoehndorf

Neural logical reasoning (NLR) is a fundamental task to explore such knowledge bases, which aims at answering multi-hop queries with logical operations based on distributed representations of queries and answers.

Logical Reasoning

OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization

1 code implementation23 May 2022 Peng Hu, Xi Peng, Hongyuan Zhu, Mohamed M. Sabry Aly, Jie Lin

Numerous network compression methods such as pruning and quantization are proposed to reduce the model size significantly, of which the key is to find suitable compression allocation (e. g., pruning sparsity and quantization codebook) of each layer.


Are Multimodal Transformers Robust to Missing Modality?

no code implementations CVPR 2022 Mengmeng Ma, Jian Ren, Long Zhao, Davide Testuggine, Xi Peng

Based on these findings, we propose a principle method to improve the robustness of Transformer models by automatically searching for an optimal fusion strategy regarding input data.

Multi-Scale Adaptive Network for Single Image Denoising

1 code implementation8 Mar 2022 Yuanbiao Gou, Peng Hu, Jiancheng Lv, Joey Tianyi Zhou, Xi Peng

AFuB devotes to adaptively sampling and transferring the features from one scale to another scale, which fuses the multi-scale features with varying characteristics from coarse to fine.

Image Denoising

All-in-One Image Restoration for Unknown Corruption

1 code implementation CVPR 2022 Boyun Li, Xiao Liu, Peng Hu, Zhongqin Wu, Jiancheng Lv, Xi Peng

In this paper, we study a challenging problem in image restoration, namely, how to develop an all-in-one method that could recover images from a variety of unknown corruption types and levels.

Image Restoration

Deep Learning for Spatiotemporal Modeling of Urbanization

no code implementations17 Dec 2021 Tang Li, Jing Gao, Xi Peng

Here we explore the capacity of deep spatial learning for the predictive modeling of urbanization.

BIG-bench Machine Learning

Learning with Noisy Correspondence for Cross-modal Matching

1 code implementation NeurIPS 2021 Zhenyu Huang, guocheng niu, Xiao Liu, Wenbiao Ding, Xinyan Xiao, Hua Wu, Xi Peng

Based on this observation, we reveal and study a latent and challenging direction in cross-modal matching, named noisy correspondence, which could be regarded as a new paradigm of noisy labels.

Cross-Modal Retrieval Memorization +2

Calibrating Probabilistic Embeddings for Cross-Modal Retrieval

no code implementations29 Sep 2021 Fengchun Qiao, Xi Peng

The key idea is to estimate the density ratio between the distributions of the two modalities, and use it to calibrate the similarity measurement in the embedding space.

Cross-Modal Retrieval Retrieval

Understanding the factors driving the opioid epidemic using machine learning

no code implementations16 Aug 2021 Sachin Gavali, Chuming Chen, Julie Cowart, Xi Peng, Shanshan Ding, Cathy Wu, Tammy Anderson

Furthermore, we discovered that, as the epidemic has shifted from legal (i. e., prescription opioids) to illegal (e. g., heroin and fentanyl) drugs in recent years, the correlation of environment, crime and health related variables with the opioid risk has increased significantly while the correlation of economic and socio-demographic variables has decreased.

BIG-bench Machine Learning

Out-of-Domain Generalization from a Single Source: An Uncertainty Quantification Approach

no code implementations5 Aug 2021 Xi Peng, Fengchun Qiao, Long Zhao

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training.

Domain Generalization Image Classification +4

Accelerated MRI Reconstruction with Separable and Enhanced Low-Rank Hankel Regularization

no code implementations24 Jul 2021 Xinlin Zhang, Hengfa Lu, Di Guo, Zongying Lai, Huihui Ye, Xi Peng, Bo Zhao, Xiaobo Qu

The combination of the sparse sampling and the low-rank structured matrix reconstruction has shown promising performance, enabling a significant reduction of the magnetic resonance imaging data acquisition time.

MRI Reconstruction

Unsupervised Neural Rendering for Image Hazing

no code implementations14 Jul 2021 Boyun Li, Yijie Lin, Xiao Liu, Peng Hu, Jiancheng Lv, Xi Peng

To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i. e., unpaired real hazy images.

Image Dehazing Neural Rendering

Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning

no code implementations28 Jun 2021 Yi Zhang, Sheng Huang, Xi Peng, Dan Yang

DCVAE conducts feature synthesis via pairing two Conditional Variational AutoEncoders (CVAEs) with the same seed but different modality conditions in a dizygotic symbiosis manner.

Data Augmentation Few-Shot Learning

COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction

1 code implementation CVPR 2021 Yijie Lin, Yuanbiao Gou, Zitao Liu, Boyun Li, Jiancheng Lv, Xi Peng

In this paper, we study two challenging problems in incomplete multi-view clustering analysis, namely, i) how to learn an informative and consistent representation among different views without the help of labels and ii) how to recover the missing views from data.

Contrastive Learning Incomplete multi-view clustering +1

Uncertainty-guided Model Generalization to Unseen Domains

no code implementations CVPR 2021 Fengchun Qiao, Xi Peng

To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization.

Domain Generalization Image Classification +6

SMIL: Multimodal Learning with Severely Missing Modality

1 code implementation9 Mar 2021 Mengmeng Ma, Jian Ren, Long Zhao, Sergey Tulyakov, Cathy Wu, Xi Peng

A common assumption in multimodal learning is the completeness of training data, i. e., full modalities are available in all training examples.


Uncertain Out-of-Domain Generalization

no code implementations1 Jan 2021 Fengchun Qiao, Xi Peng

To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization.

Domain Generalization Image Classification +5

Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization

1 code implementation CVPR 2021 Long Zhao, Yuxiao Wang, Jiaping Zhao, Liangzhe Yuan, Jennifer J. Sun, Florian Schroff, Hartwig Adam, Xi Peng, Dimitris Metaxas, Ting Liu

To evaluate the power of the learned representations, in addition to the conventional fully-supervised action recognition settings, we introduce a novel task called single-shot cross-view action recognition.

Action Recognition Contrastive Learning +1

CLEARER: Multi-Scale Neural Architecture Search for Image Restoration

1 code implementation NeurIPS 2020 Yuanbiao Gou, Boyun Li, Zitao Liu, Songfan Yang, Xi Peng

Different from the existing labor-intensive handcrafted architecture design paradigms, we present a novel method, termed as multi-sCaLe nEural ARchitecture sEarch for image Restoration (CLEARER), which is a specifically designed neural architecture search (NAS) for image restoration.

Image Denoising Image Restoration +2

Partially View-aligned Clustering

no code implementations NeurIPS 2020 Zhenyu Huang, Peng Hu, Joey Tianyi Zhou, Jiancheng Lv, Xi Peng

To solve this practical and challenging problem, we propose a novel multi-view clustering method termed partially view-aligned clustering (PVC).

Contrastive Clustering

1 code implementation21 Sep 2020 Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, Xi Peng

In this paper, we propose a one-stage online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning.

Ranked #3 on Image Clustering on STL-10 (using extra training data)

Contrastive Learning Online Clustering

Structured Graph Learning for Clustering and Semi-supervised Classification

no code implementations31 Aug 2020 Zhao Kang, Chong Peng, Qiang Cheng, Xinwang Liu, Xi Peng, Zenglin Xu, Ling Tian

Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus they might not achieve the optimal performance.

Classification General Classification +1

You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network

1 code implementation30 Jun 2020 Boyun Li, Yuanbiao Gou, Shuhang Gu, Jerry Zitao Liu, Joey Tianyi Zhou, Xi Peng

In this paper, we study two challenging and less-touched problems in single image dehazing, namely, how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and a image collection (untrained).

Disentanglement Image Dehazing +1

Heterogeneous Representation Learning: A Review

no code implementations28 Apr 2020 Joey Tianyi Zhou, Xi Peng, Yew-Soon Ong

The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Representation Learning (HRL) termed in this paper.

Multi-Task Learning MULTI-VIEW LEARNING +1

Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge

no code implementations CVPR 2020 Long Zhao, Xi Peng, Yuxiao Chen, Mubbasir Kapadia, Dimitris N. Metaxas

Our key idea is to generalize the distilled cross-modal knowledge learned from a Source dataset, which contains paired examples from both modalities, to the Target dataset by modeling knowledge as priors on parameters of the Student.

3D Hand Pose Estimation Knowledge Distillation

Learning to Learn Single Domain Generalization

1 code implementation CVPR 2020 Fengchun Qiao, Long Zhao, Xi Peng

We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training.

Domain Generalization Meta-Learning

Improving Distant Supervised Relation Extraction by Dynamic Neural Network

no code implementations15 Nov 2019 Yanjie Gou, Yinjie Lei, Lingqiao Liu, Pingping Zhang, Xi Peng

To account for this style shift, the model should adjust its parameters in accordance with entity types.

Relation Extraction

Automatic Health Problem Detection from Gait Videos Using Deep Neural Networks

1 code implementation4 Jun 2019 Rahil Mehrizi, Xi Peng, Shaoting Zhang, Ruisong Liao, Kang Li

This study presents a starting point toward a powerful tool for automatic classification of gait disorders and can be used as a basis for future applications of Deep Learning in clinical gait analysis.

Feature Engineering General Classification +2

Semantic-Guided Multi-Attention Localization for Zero-Shot Learning

no code implementations NeurIPS 2019 Yizhe Zhu, Jianwen Xie, Zhiqiang Tang, Xi Peng, Ahmed Elgammal

Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes.

Zero-Shot Learning

XAI Beyond Classification: Interpretable Neural Clustering

no code implementations22 Aug 2018 Xi Peng, Yunnan Li, Ivor W. Tsang, Hongyuan Zhu, Jiancheng Lv, Joey Tianyi Zhou

The second is implementing discrete $k$-means with a differentiable neural network that embraces the advantages of parallel computing, online clustering, and clustering-favorable representation learning.

Classification Online Clustering +1

Quantized Densely Connected U-Nets for Efficient Landmark Localization

1 code implementation ECCV 2018 Zhiqiang Tang, Xi Peng, Shijie Geng, Lingfei Wu, Shaoting Zhang, Dimitris Metaxas

Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers.

Face Alignment Pose Estimation

Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

1 code implementation ECCV 2018 Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris Metaxas

We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object.

Human Pose Forecasting Image to Video Generation +1

CR-GAN: Learning Complete Representations for Multi-view Generation

1 code implementation28 Jun 2018 Yu Tian, Xi Peng, Long Zhao, Shaoting Zhang, Dimitris N. Metaxas

Generating multi-view images from a single-view input is an essential yet challenging problem.

Self-Supervised Learning

Toward Marker-free 3D Pose Estimation in Lifting: A Deep Multi-view Solution

no code implementations6 Feb 2018 Rahil Mehrizi, Xi Peng, Zhiqiang Tang, Xu Xu, Dimitris Metaxas, Kang Li

The results are also compared with state-of-the-art methods on HumanEva-I dataset, which demonstrates the superior performance of our approach.

3D Pose Estimation

RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment

no code implementations17 Jan 2018 Xi Peng, Rogerio S. Feris, Xiaoyu Wang, Dimitris N. Metaxas

We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model.

Face Alignment

Deep Sparse Subspace Clustering

no code implementations25 Sep 2017 Xi Peng, Jiashi Feng, Shijie Xiao, Jiwen Lu, Zhang Yi, Shuicheng Yan

In this paper, we present a deep extension of Sparse Subspace Clustering, termed Deep Sparse Subspace Clustering (DSSC).

Cartoonish sketch-based face editing in videos using identity deformation transfer

no code implementations25 Mar 2017 Long Zhao, Fangda Han, Xi Peng, Xun Zhang, Mubbasir Kapadia, Vladimir Pavlovic, Dimitris N. Metaxas

We first recover the facial identity and expressions from the video by fitting a face morphable model for each frame.

Face Model

Reconstruction-Based Disentanglement for Pose-invariant Face Recognition

no code implementations ICCV 2017 Xi Peng, Xiang Yu, Kihyuk Sohn, Dimitris Metaxas, Manmohan Chandraker

Finally, we propose a new feature reconstruction metric learning to explicitly disentangle identity and pose, by demanding alignment between the feature reconstructions through various combinations of identity and pose features, which is obtained from two images of the same subject.

Disentanglement Face Recognition +2

Track Facial Points in Unconstrained Videos

no code implementations9 Sep 2016 Xi Peng, Qiong Hu, Junzhou Huang, Dimitris N. Metaxas

Our approach takes advantage of part-based representation and cascade regression for robust and efficient alignment on each frame.

Incremental Learning

A Recurrent Encoder-Decoder Network for Sequential Face Alignment

no code implementations19 Aug 2016 Xi Peng, Rogerio S. Feris, Xiaoyu Wang, Dimitris N. Metaxas

We propose a novel recurrent encoder-decoder network model for real-time video-based face alignment.

Face Alignment

PIEFA: Personalized Incremental and Ensemble Face Alignment

no code implementations ICCV 2015 Xi Peng, Shaoting Zhang, Yu Yang, Dimitris N. Metaxas

Face alignment, especially on real-time or large-scale sequential images, is a challenging task with broad applications.

Face Alignment Incremental Learning

Connections Between Nuclear Norm and Frobenius Norm Based Representations

no code implementations26 Feb 2015 Xi Peng, Can-Yi Lu, Zhang Yi, Huajin Tang

A lot of works have shown that frobenius-norm based representation (FNR) is competitive to sparse representation and nuclear-norm based representation (NNR) in numerous tasks such as subspace clustering.

Automatic Subspace Learning via Principal Coefficients Embedding

no code implementations17 Nov 2014 Xi Peng, Jiwen Lu, Zhang Yi, Rui Yan

In this paper, we address two challenging problems in unsupervised subspace learning: 1) how to automatically identify the feature dimension of the learned subspace (i. e., automatic subspace learning), and 2) how to learn the underlying subspace in the presence of Gaussian noise (i. e., robust subspace learning).

Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification

no code implementations22 Sep 2014 Xi Peng, Rui Yan, Bo Zhao, Huajin Tang, Zhang Yi

Although the methods achieve a higher recognition rate than the traditional SPM, they consume more time to encode the local descriptors extracted from the image.

General Classification Image Classification +1

A Unified Framework for Representation-based Subspace Clustering of Out-of-sample and Large-scale Data

no code implementations25 Sep 2013 Xi Peng, Huajin Tang, Lei Zhang, Zhang Yi, Shijie Xiao

In this paper, we propose a unified framework which makes representation-based subspace clustering algorithms feasible to cluster both out-of-sample and large-scale data.

Scalable Sparse Subspace Clustering

no code implementations CVPR 2013 Xi Peng, Lei Zhang, Zhang Yi

To address the problems, this paper proposes out-of-sample extension of SSC, named as Scalable Sparse Subspace Clustering (SSSC), which makes SSC feasible to cluster large scale data sets.

Motion Segmentation Online Clustering

Locally linear representation for image clustering

no code implementations24 Apr 2013 Liangli Zhen, Zhang Yi, Xi Peng, Dezhong Peng

There are two popular schemes to construct a similarity graph, i. e., pairwise distance based scheme and linear representation based scheme.

Image Clustering

Learning Locality-Constrained Collaborative Representation for Face Recognition

no code implementations4 Oct 2012 Xi Peng, Lei Zhang, Zhang Yi, Kok Kiong Tan

The model of low-dimensional manifold and sparse representation are two well-known concise models that suggest each data can be described by a few characteristics.

Dimensionality Reduction Face Recognition

Constructing the L2-Graph for Robust Subspace Learning and Subspace Clustering

no code implementations5 Sep 2012 Xi Peng, Zhiding Yu, Huajin Tang, Zhang Yi

Under the framework of graph-based learning, the key to robust subspace clustering and subspace learning is to obtain a good similarity graph that eliminates the effects of errors and retains only connections between the data points from the same subspace (i. e., intra-subspace data points).

Image Clustering Motion Segmentation

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