Search Results for author: Xinghao Ding

Found 56 papers, 14 papers with code

Double Normalizing Flows: Flexible Bayesian Gaussian Process ODEs Learning

no code implementations17 Sep 2023 Jian Xu, Shian Du, Junmei Yang, Xinghao Ding, John Paisley, Delu Zeng

To address this limitation, we incorporate normalizing flows to reparameterize the vector field of ODEs, resulting in a more flexible and expressive prior distribution.

Bayesian Inference Gaussian Processes +2

Learning a Simple Low-Light Image Enhancer From Paired Low-Light Instances

1 code implementation CVPR 2023 Zhenqi Fu, Yan Yang, Xiaotong Tu, Yue Huang, Xinghao Ding, Kai-Kuang Ma

Those solutions, however, often fail in revealing image details due to the limited information in a single image and the poor adaptability of handcrafted priors.

Low-Light Image Enhancement

Hint-dynamic Knowledge Distillation

no code implementations30 Nov 2022 Yiyang Liu, Chenxin Li, Xiaotong Tu, Xinghao Ding, Yue Huang

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model.

Knowledge Distillation

Uncertainty Inspired Underwater Image Enhancement

1 code implementation20 Jul 2022 Zhenqi Fu, Wu Wang, Yue Huang, Xinghao Ding, Kai-Kuang Ma

After that, we adopt a consensus process to predict a deterministic result based on a set of samples from the distribution.


Knowledge Condensation Distillation

2 code implementations12 Jul 2022 Chenxin Li, Mingbao Lin, Zhiyuan Ding, Nie Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Liujuan Cao

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher network to strengthen a smaller student.

Knowledge Distillation

Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection

no code implementations6 Jun 2022 Chaoqi Chen, Jiongcheng Li, Hong-Yu Zhou, Xiaoguang Han, Yue Huang, Xinghao Ding, Yizhou Yu

However, both the global and local alignment approaches fail to capture the topological relations among different foreground objects as the explicit dependencies and interactions between and within domains are neglected.

Domain Adaptation Graph Attention +4

A Closer Look at Personalization in Federated Image Classification

no code implementations22 Apr 2022 Changxing Jing, Yan Huang, Yihong Zhuang, Liyan Sun, Yue Huang, Zhenlong Xiao, Xinghao Ding

This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning.

Classification Edge-computing +3

AFSC: Adaptive Fourier Space Compression for Anomaly Detection

no code implementations17 Apr 2022 Haote Xu, Yunlong Zhang, Liyan Sun, Chenxin Li, Yue Huang, Xinghao Ding

Data augmentation based methods construct pseudo-healthy images by "pasting" fake lesions on real healthy ones, and a network is trained to predict healthy images in a supervised manner.

Anomaly Detection Data Augmentation

Acoustic-Net: A Novel Neural Network for Sound Localization and Quantification

no code implementations31 Mar 2022 Guanxing Zhou, Hao Liang, Xinghao Ding, Yue Huang, Xiaotong Tu, Saqlain Abbas

Acoustic source localization has been applied in different fields, such as aeronautics and ocean science, generally using multiple microphones array data to reconstruct the source location.

Harmonizing Pathological and Normal Pixels for Pseudo-healthy Synthesis

1 code implementation29 Mar 2022 Yunlong Zhang, Xin Lin, Yihong Zhuang, LiyanSun, Yue Huang, Xinghao Ding, Guisheng Wang, Lin Yang, Yizhou Yu

Comprehensive experiments on the T2 modality of BraTS demonstrate that the proposed method substantially outperforms the state-of-the-art methods.

Image Enhancement Image Segmentation +3

Self-Verification in Image Denoising

no code implementations1 Nov 2021 Huangxing Lin, Yihong Zhuang, Delu Zeng, Yue Huang, Xinghao Ding, John Paisley

Specifically, we treat the output of the network as a ``prior'' that we denoise again after ``re-noising''.

Image Denoising

Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation

no code implementations31 May 2021 Chenxin Li, Wenao Ma, Liyan Sun, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu

In this paper, to address the above issues, we propose a hierarchical deep network where an attention mechanism localizes the low-contrast capillary regions guided by the whole vessels, and enhance the spatial activation in those areas for the sub-type vessels.


I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors

1 code implementation CVPR 2021 Chaoqi Chen, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu

Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers.

Region Proposal

Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation

no code implementations16 Mar 2021 Chenxin Li, Yunlong Zhang, Jiongcheng Li, Yue Huang, Xinghao Ding

In this paper, to alleviate this issue, we introduce the semantic space of healthy anatomy in the process of modeling healthy-data distribution.

Anatomy Anomaly Detection +2

Consistent Posterior Distributions under Vessel-Mixing: A Regularization for Cross-Domain Retinal Artery/Vein Classification

no code implementations16 Mar 2021 Chenxin Li, Yunlong Zhang, Zhehan Liang, Wenao Ma, Yue Huang, Xinghao Ding

In this paper, we propose a novel vessel-mixing based consistency regularization framework, for cross-domain learning in retinal A/V classification.

Classification General Classification

Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement

1 code implementation1 Feb 2021 Zhenqi Fu, Xueyang Fu, Yue Huang, Xinghao Ding

Our approach, termed Twice Mixing, is motivated by the observation that a mid-quality image can be generated by mixing a high-quality image with its low-quality version.


Underwater Image Enhancement via Learning Water Type Desensitized Representations

1 code implementation1 Feb 2021 Zhenqi Fu, Xiaopeng Lin, Wu Wang, Yue Huang, Xinghao Ding

Specifically, we apply whitening to de-correlate activations across spatial dimensions for each instance in a mini-batch.

Image Enhancement Vocal Bursts Type Prediction

Dual Bipartite Graph Learning: A General Approach for Domain Adaptive Object Detection

no code implementations ICCV 2021 Chaoqi Chen, Jiongcheng Li, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu

Domain Adaptive Object Detection (DAOD) relieves the reliance on large-scale annotated data by transferring the knowledge learned from a labeled source domain to a new unlabeled target domain.

Domain Adaptation Graph Learning +2

TRAR: Routing the Attention Spans in Transformer for Visual Question Answering

1 code implementation ICCV 2021 Yiyi Zhou, Tianhe Ren, Chaoyang Zhu, Xiaoshuai Sun, Jianzhuang Liu, Xinghao Ding, Mingliang Xu, Rongrong Ji

Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks.

Question Answering Referring Expression +2

Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding

no code implementations10 Dec 2020 Liyan Sun, Chenxin Li, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu

Motivated by the spatial consistency and regularity in medical images, we developed an efficient global correlation module to capture the correlation between a support and query image and incorporate it into the deep network called global correlation network.

Clustering Image Segmentation +2

Adaptive noise imitation for image denoising

no code implementations30 Nov 2020 Huangxing Lin, Yihong Zhuang, Yue Huang, Xinghao Ding, Yizhou Yu, Xiaoqing Liu, John Paisley

Coupling the noisy data output from ADANI with the corresponding ground-truth, a denoising CNN is then trained in a fully-supervised manner.

Image Denoising

A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision

1 code implementation23 Oct 2020 Liyan Sun, Jianxiong Wu, Xinghao Ding, Yue Huang, Guisheng Wang, Yizhou Yu

We further proposed a localization branch realized via an aggregation of high-level features in a deep decoder to predict locations of organ and lesion, which enriches student segmentor with precise localization information.

Image Segmentation Lesion Segmentation +2

Hard Class Rectification for Domain Adaptation

1 code implementation8 Aug 2020 Yunlong Zhang, Changxing Jing, Huangxing Lin, Chaoqi Chen, Yue Huang, Xinghao Ding, Yang Zou

Second, we further consider that the predictions of target samples belonging to the hard class are vulnerable to perturbations.

Semi-supervised Domain Adaptation Unsupervised Domain Adaptation

Multi-Task Neural Networks with Spatial Activation for Retinal Vessel Segmentation and Artery/Vein Classification

no code implementations18 Jul 2020 Wenao Ma, Shuang Yu, Kai Ma, Jiexiang Wang, Xinghao Ding, Yefeng Zheng

In this paper, we propose a multi-task deep neural network with spatial activation mechanism that is able to segment full retinal vessel, artery and vein simultaneously, without the pre-requirement of vessel segmentation.

Classification General Classification +2

Harmonizing Transferability and Discriminability for Adapting Object Detectors

1 code implementation CVPR 2020 Chaoqi Chen, Zebiao Zheng, Xinghao Ding, Yue Huang, Qi Dou

Recent advances in adaptive object detection have achieved compelling results in virtue of adversarial feature adaptation to mitigate the distributional shifts along the detection pipeline.

object-detection Weakly Supervised Object Detection

A Real-time Global Inference Network for One-stage Referring Expression Comprehension

1 code implementation7 Dec 2019 Yiyi Zhou, Rongrong Ji, Gen Luo, Xiaoshuai Sun, Jinsong Su, Xinghao Ding, Chia-Wen Lin, Qi Tian

Referring Expression Comprehension (REC) is an emerging research spot in computer vision, which refers to detecting the target region in an image given an text description.

feature selection Referring Expression +1

Noise2Blur: Online Noise Extraction and Denoising

no code implementations3 Dec 2019 Huangxing Lin, Weihong Zeng, Xinghao Ding, Xueyang Fu, Yue Huang, John Paisley

Using the new image pair, the denoising network learns to generate clean and high-quality images from noisy observations.

Image Denoising

Learning Rate Dropout

1 code implementation30 Nov 2019 Huangxing Lin, Weihong Zeng, Xinghao Ding, Yue Huang, Chenxi Huang, John Paisley

The uncertainty of the descent path helps the model avoid saddle points and bad local minima.

Multi-sequence Cardiac MR Segmentation with Adversarial Domain Adaptation Network

no code implementations28 Oct 2019 Jiexiang Wang, Hongyu Huang, Chaoqi Chen, Wenao Ma, Yue Huang, Xinghao Ding

Automatic and accurate segmentation of the ventricles and myocardium from multi-sequence cardiac MRI (CMR) is crucial for the diagnosis and treatment management for patients suffering from myocardial infarction (MI).

Domain Adaptation Management +1

Uncertainty-Guided Domain Alignment for Layer Segmentation in OCT Images

no code implementations22 Aug 2019 Jiexiang Wang, Cheng Bian, Meng Li, Xin Yang, Kai Ma, Wenao Ma, Jin Yuan, Xinghao Ding, Yefeng Zheng

Automatic and accurate segmentation for retinal and choroidal layers of Optical Coherence Tomography (OCT) is crucial for detection of various ocular diseases.


Unsupervised Adversarial Graph Alignment with Graph Embedding

no code implementations1 Jul 2019 Chaoqi Chen, Weiping Xie, Tingyang Xu, Yu Rong, Wenbing Huang, Xinghao Ding, Yue Huang, Junzhou Huang

In this paper, we propose an Unsupervised Adversarial Graph Alignment (UAGA) framework to learn a cross-graph alignment between two embedding spaces of different graphs in a fully unsupervised fashion (\emph{i. e.,} no existing anchor links and no users' personal profile or attribute information is available).

Graph Embedding Link Prediction

Rain O'er Me: Synthesizing real rain to derain with data distillation

no code implementations9 Apr 2019 Huangxing Lin, Yanlong Li, Xinghao Ding, Weihong Zeng, Yue Huang, John Paisley

We present a supervised technique for learning to remove rain from images without using synthetic rain software.

Rain Removal

A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal

no code implementations24 Nov 2018 Huangxing Lin, Xueyang Fu, Changxing Jing, Xinghao Ding, Yue Huang

Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens.

Rain Removal

A Deep Tree-Structured Fusion Model for Single Image Deraining

no code implementations21 Nov 2018 Xueyang Fu, Qi Qi, Yue Huang, Xinghao Ding, Feng Wu, John Paisley

We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem.

Single Image Deraining

An Adversarial Learning Approach to Medical Image Synthesis for Lesion Detection

no code implementations25 Oct 2018 Liyan Sun, Jiexiang Wang, Yue Huang, Xinghao Ding, Hayit Greenspan, John Paisley

Being able to provide a "normal" counterpart to a medical image can provide useful side information for medical imaging tasks like lesion segmentation or classification validated by our experiments.

Data Augmentation General Classification +5

Lightweight Pyramid Networks for Image Deraining

no code implementations16 May 2018 Xueyang Fu, Borong Liang, Yue Huang, Xinghao Ding, John Paisley

In this paper, we propose a lightweight pyramid of networks (LPNet) for single image deraining.

Single Image Deraining

A Deeply-Recursive Convolutional Network for Crowd Counting

no code implementations15 May 2018 Xinghao Ding, Zhirui Lin, Fujin He, Yu Wang, Yue Huang

The estimation of crowd count in images has a wide range of applications such as video surveillance, traffic monitoring, public safety and urban planning.

Crowd Counting

Residual-Guide Feature Fusion Network for Single Image Deraining

no code implementations20 Apr 2018 Zhiwen Fan, Huafeng Wu, Xueyang Fu, Yue Hunag, Xinghao Ding

Single image rain streaks removal is extremely important since rainy images adversely affect many computer vision systems.

Single Image Deraining Test

A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstruction

no code implementations10 Apr 2018 Liyan Sun, Zhiwen Fan, Yue Huang, Xinghao Ding, John Paisley

In multi-contrast magnetic resonance imaging (MRI), compressed sensing theory can accelerate imaging by sampling fewer measurements within each contrast.

MRI Reconstruction

A Divide-and-Conquer Approach to Compressed Sensing MRI

no code implementations27 Mar 2018 Liyan Sun, Zhiwen Fan, Xinghao Ding, Congbo Cai, Yue Huang, John Paisley

Compressed sensing (CS) theory assures us that we can accurately reconstruct magnetic resonance images using fewer k-space measurements than the Nyquist sampling rate requires.

A Deep Error Correction Network for Compressed Sensing MRI

no code implementations23 Mar 2018 Liyan Sun, Zhiwen Fan, Yue Huang, Xinghao Ding, John Paisley

Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction.

MRI Reconstruction

PanNet: A Deep Network Architecture for Pan-Sharpening

no code implementations ICCV 2017 Junfeng Yang, Xueyang Fu, Yuwen Hu, Yue Huang, Xinghao Ding, John Paisley

We incorporate domain-specific knowledge to design our PanNet architecture by focusing on the two aims of the pan-sharpening problem: spectral and spatial preservation.

Removing Rain From Single Images via a Deep Detail Network

no code implementations CVPR 2017 Xueyang Fu, Jia-Bin Huang, Delu Zeng, Yue Huang, Xinghao Ding, John Paisley

We propose a new deep network architecture for removing rain streaks from individual images based on the deep convolutional neural network (CNN).

Denoising Rain Removal +1

Saliency Detection with Spaces of Background-based Distribution

no code implementations17 Mar 2016 Tong Zhao, Lin Li, Xinghao Ding, Yue Huang, Delu Zeng

In this letter, an effective image saliency detection method is proposed by constructing some novel spaces to model the background and redefine the distance of the salient patches away from the background.

Saliency Detection

Pan-Sharpening With a Hyper-Laplacian Penalty

no code implementations ICCV 2015 Yiyong Jiang, Xinghao Ding, Delu Zeng, Yue Huang, John Paisley

Our objective incorporates the L1/2-norm in a way that can leverage recent computationally efficient methods, and L1 for which the alternating direction method of multipliers can be used.

Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI

no code implementations12 Feb 2013 Yue Huang, John Paisley, Qin Lin, Xinghao Ding, Xueyang Fu, Xiao-Ping Zhang

The size of the dictionary and the patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables.

Denoising Dictionary Learning +2

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