Search Results for author: Xin Yang

Found 130 papers, 40 papers with code

Label Inference Attack against Split Learning under Regression Setting

no code implementations18 Jan 2023 Shangyu Xie, Xin Yang, Yuanshun Yao, Tianyi Liu, Taiqing Wang, Jiankai Sun

In this work, we step further to study the leakage in the scenario of the regression model, where the private labels are continuous numbers (instead of discrete labels in classification).

Federated Learning Inference Attack +1

CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction

no code implementations7 Jan 2023 Gangwei Xu, Huan Zhou, Xin Yang

In this paper, we propose CGI-Stereo, a novel neural network architecture that can concurrently achieve real-time performance, state-of-the-art accuracy, and strong generalization ability.

Stereo Matching

Photo-Realistic Out-of-domain GAN inversion via Invertibility Decomposition

1 code implementation19 Dec 2022 Xin Yang, Xiaogang Xu, Yingcong Chen

In this paper, we propose a novel framework that enhances the fidelity of human face inversion by designing a new module to decompose the input images to ID and OOD partitions with invertibility masks.

Affinity Feature Strengthening for Accurate, Complete and Robust Vessel Segmentation

1 code implementation12 Nov 2022 Tianyi Shi, Xiaohuan Ding, Wei Zhou, Feng Pan, Zengqiang Yan, Xiang Bai, Xin Yang

In this paper, we present a novel affinity feature strengthening network (AFN) which adopts a contrast-insensitive approach based on multiscale affinity to jointly model topology and refine pixel-wise segmentation features.

An Attention-Guided and Wavelet-Constrained Generative Adversarial Network for Infrared and Visible Image Fusion

no code implementations20 Oct 2022 Xiaowen Liu, Renhua Wang, Hongtao Huo, Xin Yang, Jing Li

The GAN-based infrared and visible image fusion methods have gained ever-increasing attention due to its effectiveness and superiority.

Infrared And Visible Image Fusion

Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions

no code implementations15 Oct 2022 Hongkuan Shi, Zhiwei Wang, Ying Zhou, Dun Li, Xin Yang, Qiang Li

The learned knowledge flows across branches along two directions: a cross direction (disparity guides distribution in ACS) and a parallel direction (disparity guides disparity in APS).

3D Reconstruction Disparity Estimation

Hierarchical and Progressive Image Matting

no code implementations13 Oct 2022 Yu Qiao, Yuhao Liu, Ziqi Wei, Yuxin Wang, Qiang Cai, Guofeng Zhang, Xin Yang

In this paper, we propose an end-to-end Hierarchical and Progressive Attention Matting Network (HAttMatting++), which can better predict the opacity of the foreground from single RGB images without additional input.

Image Matting SSIM

Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting

no code implementations13 Oct 2022 Yu Qiao, Ziqi Wei, Yuhao Liu, Yuxin Wang, Dongsheng Zhou, Qiang Zhang, Xin Yang

This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting.

Image Matting

Point Cloud Scene Completion with Joint Color and Semantic Estimation from Single RGB-D Image

no code implementations12 Oct 2022 Zhaoxuan Zhang, Xiaoguang Han, Bo Dong, Tong Li, BaoCai Yin, Xin Yang

Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view RGB-D and segmentation map, and integrating all RGB-D and segmentation maps into the point cloud.

Image Inpainting Semantic Segmentation

Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images

1 code implementation9 Oct 2022 Yu Cai, Hao Chen, Xin Yang, Yu Zhou, Kwang-Ting Cheng

Due to the high-cost annotations of abnormal images, most methods utilize only known normal images during training and identify samples not conforming to the normal profile as anomalies in the testing phase.

Anomaly Detection Self-Supervised Learning

Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning

no code implementations24 Sep 2022 Xin Yang, Omid Ardakanian

This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the collected sensor data have different underlying distributions.

Meta-Learning Personalized Federated Learning

Accurate and Efficient Stereo Matching via Attention Concatenation Volume

3 code implementations23 Sep 2022 Gangwei Xu, Yun Wang, Junda Cheng, Jinhui Tang, Xin Yang

In this paper, we present a novel cost volume construction method, named attention concatenation volume (ACV), which generates attention weights from correlation clues to suppress redundant information and enhance matching-related information in the concatenation volume.

Stereo Matching

Deep Learning for Medical Image Segmentation: Tricks, Challenges and Future Directions

1 code implementation21 Sep 2022 Dong Zhang, Yi Lin, Hao Chen, Zhuotao Tian, Xin Yang, Jinhui Tang, Kwang Ting Cheng

Over the past few years, the rapid development of deep learning technologies for computer vision has greatly promoted the performance of medical image segmentation (MedISeg).

Data Augmentation Domain Adaptation +3

Progressive Glass Segmentation

no code implementations6 Sep 2022 Letian Yu, Haiyang Mei, Wen Dong, Ziqi Wei, Li Zhu, Yuxin Wang, Xin Yang

First, we attempt to bridge the characteristic gap between different levels of features by developing a Discriminability Enhancement (DE) module which enables level-specific features to be a more discriminative representation, alleviating the features incompatibility for fusion.

DPAUC: Differentially Private AUC Computation in Federated Learning

1 code implementation25 Aug 2022 Jiankai Sun, Xin Yang, Yuanshun Yao, Junyuan Xie, Di wu, Chong Wang

Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants.

Federated Learning

Real-time Streaming Video Denoising with Bidirectional Buffers

1 code implementation14 Jul 2022 Chenyang Qi, Junming Chen, Xin Yang, Qifeng Chen

Recent multi-output inference works propagate the bidirectional temporal feature with a parallel or recurrent framework, which either suffers from performance drops on the temporal edges of clips or can not achieve online inference.

Denoising Video Denoising

Multi-Attribute Attention Network for Interpretable Diagnosis of Thyroid Nodules in Ultrasound Images

no code implementations9 Jul 2022 Van T. Manh, Jianqiao Zhou, Xiaohong Jia, Zehui Lin, Wenwen Xu, Zihan Mei, Yijie Dong, Xin Yang, Ruobing Huang, Dong Ni

To overcome this, we propose a novel deep learning framework called multi-attribute attention network (MAA-Net) that is designed to mimic the clinical diagnosis process.

Fine-grained Correlation Loss for Regression

no code implementations1 Jul 2022 Chaoyu Chen, Xin Yang, Ruobing Huang, Xindi Hu, Yankai Huang, Xiduo Lu, Xinrui Zhou, Mingyuan Luo, Yinyu Ye, Xue Shuang, Juzheng Miao, Yi Xiong, Dong Ni

In this work, we propose to revisit the classic regression tasks with novel investigations on directly optimizing the fine-grained correlation losses.

Image Quality Assessment object-detection +2

Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling

no code implementations1 Jul 2022 Jiamin Liang, Xin Yang, Yuhao Huang, Kai Liu, Xinrui Zhou, Xindi Hu, Zehui Lin, Huanjia Luo, Yuanji Zhang, Yi Xiong, Dong Ni

First, leveraging the advantages of self- and fully-supervised learning, our proposed system is trained in weakly-supervised manner for keypoint detection.

Keypoint Detection

Agent with Tangent-based Formulation and Anatomical Perception for Standard Plane Localization in 3D Ultrasound

no code implementations1 Jul 2022 Yuxin Zou, Haoran Dou, Yuhao Huang, Xin Yang, Jikuan Qian, Chaojiong Zhen, Xiaodan Ji, Nishant Ravikumar, Guoqiang Chen, Weijun Huang, Alejandro F. Frangi, Dong Ni

First, we formulate SP localization in 3D US as a tangent-point-based problem in RL to restructure the action space and significantly reduce the search space.

Anatomy

Federated Learning with Imbalanced and Agglomerated Data Distribution for Medical Image Classification

no code implementations28 Jun 2022 Nannan Wu, Li Yu, Xin Yang, Kwang-Ting Cheng, Zengqiang Yan

Inspired by real medical imaging datasets, we identify and formulate a new and more realistic data distribution denoted as L2 distribution where global class distribution is highly imbalanced and data distributions across clients are imbalanced but forming a certain degree of data agglomeration.

Contrastive Learning Federated Learning +3

Differentially Private Multi-Party Data Release for Linear Regression

no code implementations16 Jun 2022 Ruihan Wu, Xin Yang, Yuanshun Yao, Jiankai Sun, Tianyi Liu, Kilian Q. Weinberger, Chong Wang

Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects.

regression

Dual-Distribution Discrepancy for Anomaly Detection in Chest X-Rays

1 code implementation8 Jun 2022 Yu Cai, Hao Chen, Xin Yang, Yu Zhou, Kwang-Ting Cheng

Subsequently, inter-discrepancy between the two modules, and intra-discrepancy inside the module that is trained on only normal images are designed as anomaly scores to indicate anomalies.

Anomaly Detection

Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs

no code implementations5 Jun 2022 Zhiwei Wang, Jinxin Lv, Yunqiao Yang, Yuanhuai Liang, Yi Lin, Qiang Li, Xin Li, Xin Yang

Vertebral landmark localization is a crucial step for variant spine-related clinical applications, which requires detecting the corner points of 17 vertebrae.

Differentially Private AUC Computation in Vertical Federated Learning

no code implementations24 May 2022 Jiankai Sun, Xin Yang, Yuanshun Yao, Junyuan Xie, Di wu, Chong Wang

In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL.

Federated Learning

FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation

1 code implementation4 May 2022 Jeffry Wicaksana, Zengqiang Yan, Dong Zhang, Xijie Huang, Huimin Wu, Xin Yang, Kwang-Ting Cheng

To relax this assumption, in this work, we propose a label-agnostic unified federated learning framework, named FedMix, for medical image segmentation based on mixed image labels.

Federated Learning Image Segmentation +3

Sketch guided and progressive growing GAN for realistic and editable ultrasound image synthesis

no code implementations14 Apr 2022 Jiamin Liang, Xin Yang, Yuhao Huang, Haoming Li, Shuangchi He, Xindi Hu, Zejian Chen, Wufeng Xue, Jun Cheng, Dong Ni

Our main contributions include: 1) we present the first work that can synthesize realistic B-mode US images with high-resolution and customized texture editing features; 2) to enhance structural details of generated images, we propose to introduce auxiliary sketch guidance into a conditional GAN.

Image Generation

HASA: Hybrid Architecture Search with Aggregation Strategy for Echinococcosis Classification and Ovary Segmentation in Ultrasound Images

no code implementations14 Apr 2022 Jikuan Qian, Rui Li, Xin Yang, Yuhao Huang, Mingyuan Luo, Zehui Lin, Wenhui Hong, Ruobing Huang, Haining Fan, Dong Ni, Jun Cheng

The hybrid framework consists of a pre-trained backbone and several searched cells (i. e., network building blocks), which takes advantage of the strengths of both NAS and the expert knowledge from existing convolutional neural networks.

Image Classification Neural Architecture Search

FSOINet: Feature-Space Optimization-Inspired Network for Image Compressive Sensing

1 code implementation12 Apr 2022 Wenjun Chen, Chunling Yang, Xin Yang

In recent years, deep learning-based image compressive sensing (ICS) methods have achieved brilliant success.

Compressive Sensing

Bi-directional Object-context Prioritization Learning for Saliency Ranking

1 code implementation CVPR 2022 Xin Tian, Ke Xu, Xin Yang, Lin Du, BaoCai Yin, Rynson W. H. Lau

We observe that spatial attention works concurrently with object-based attention in the human visual recognition system.

Differentially Private Label Protection in Split Learning

no code implementations4 Mar 2022 Xin Yang, Jiankai Sun, Yuanshun Yao, Junyuan Xie, Chong Wang

Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attributes).

Label Leakage and Protection from Forward Embedding in Vertical Federated Learning

no code implementations2 Mar 2022 Jiankai Sun, Xin Yang, Yuanshun Yao, Chong Wang

As the raw labels often contain highly sensitive information, some recent work has been proposed to prevent the label leakage from the backpropagated gradients effectively in vFL.

Federated Learning

AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images

1 code implementation14 Jan 2022 Kai-Ni Wang, Xin Yang, Juzheng Miao, Lei LI, Jing Yao, Ping Zhou, Wufeng Xue, Guang-Quan Zhou, Xiahai Zhuang, Dong Ni

Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods.

Spiking Transformers for Event-Based Single Object Tracking

no code implementations CVPR 2022 Jiqing Zhang, Bo Dong, Haiwei Zhang, Jianchuan Ding, Felix Heide, BaoCai Yin, Xin Yang

In particular, the proposed architecture features a transformer module to provide global spatial information and a spiking neural network (SNN) module for extracting temporal cues.

Object Tracking

Glass Segmentation Using Intensity and Spectral Polarization Cues

no code implementations CVPR 2022 Haiyang Mei, Bo Dong, Wen Dong, Jiaxi Yang, Seung-Hwan Baek, Felix Heide, Pieter Peers, Xiaopeng Wei, Xin Yang

Transparent and semi-transparent materials pose significant challenges for existing scene understanding and segmentation algorithms due to their lack of RGB texture which impedes the extraction of meaningful features.

Scene Understanding

SECP-Net: SE-Connection Pyramid Network of Organ At Risk Segmentation for Nasopharyngeal Carcinoma

no code implementations28 Dec 2021 Zexi Huang, Lihua Guo, Xin Yang, Sijuan Huang

SECP-Net extracts global and multi-size information flow with se connection (SEC) modules and a pyramid structure of network for improving the segmentation performance, especially that of small organs.

Computed Tomography (CT) Image Segmentation +2

Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization

1 code implementation CVPR 2022 Ziqi Zhou, Lei Qi, Xin Yang, Dong Ni, Yinghuan Shi

For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain?

Domain Generalization Image Segmentation +2

CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

no code implementations11 Dec 2021 Yu Qiao, Jincheng Zhu, Chengjiang Long, Zeyao Zhang, Yuxin Wang, Zhenjun Du, Xin Yang

Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations.

Active Learning Semantic Segmentation

Learning to Detect Instance-level Salient Objects Using Complementary Image Labels

no code implementations19 Nov 2021 Xin Tian, Ke Xu, Xin Yang, BaoCai Yin, Rynson W. H. Lau

However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels.

Boundary Detection Object Localization +1

Automated Pulmonary Embolism Detection from CTPA Images Using an End-to-End Convolutional Neural Network

no code implementations10 Nov 2021 Yi Lin, Jianchao Su, Xiang Wang, Xiang Li, Jingen Liu, Kwang-Ting Cheng, Xin Yang

We have evaluated our approach using the 20 CTPA test dataset from the PE challenge, achieving a sensitivity of 78. 9%, 80. 7% and 80. 7% at 2 false positives per volume at 0mm, 2mm and 5mm localization error, which is superior to the state-of-the-art methods.

Pulmonary Embolism Detection

Monocular Depth Estimation with Sharp Boundary

no code implementations12 Oct 2021 Xin Yang, Qingling Chang, Xinlin Liu, Yan Cui

In order to mitigate the boundary blur problem, we focus on the above two impact factors.

Monocular Depth Estimation Scene Understanding

Object Tracking by Jointly Exploiting Frame and Event Domain

3 code implementations ICCV 2021 Jiqing Zhang, Xin Yang, Yingkai Fu, Xiaopeng Wei, BaoCai Yin, Bo Dong

Our approach's effectiveness is enforced by a novel designed cross-domain attention schemes, which can effectively enhance features based on self- and cross-domain attention schemes; The adaptiveness is guarded by a specially designed weighting scheme, which can adaptively balance the contribution of the two domains.

Object Tracking

Self-supervised Representation Learning for Trip Recommendation

no code implementations2 Sep 2021 Qiang Gao, Wei Wang, Kunpeng Zhang, Xin Yang, Congcong Miao

Although recent deep recursive models (e. g., RNN) are capable of alleviating these concerns, existing solutions hardly recognize the practical reality, such as the diversity of tourist demands, uncertainties in the trip generation, and the complex visiting preference.

Contrastive Learning point of interests +1

WRICNet:A Weighted Rich-scale Inception Coder Network for Multi-Resolution Remote Sensing Image Change Detection

no code implementations18 Aug 2021 Yu Jiang, Lei Hu, Yongmei Zhang, Xin Yang

With the purpose of improving change detection effectiveness of the model in the multi-resolution data set, a weighted rich-scale inception coder network (WRICNet) is proposed in this article, which can make a great fusion of shallow multi-scale features, and deep multi-scale features.

Change Detection

Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking

no code implementations10 Aug 2021 Jiqing Zhang, Kai Zhao, Bo Dong, Yingkai Fu, Yuxin Wang, Xin Yang, BaoCai Yin

Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking.

Visual Object Tracking

Deep graph matching meets mixed-integer linear programming: Relax at your own risk ?

2 code implementations1 Aug 2021 Zhoubo Xu, Puqing Chen, Romain Raveaux, Xin Yang, Huadong Liu

Graph matching is an important problem that has received widespread attention, especially in the field of computer vision.

Graph Matching

Prior-Induced Information Alignment for Image Matting

no code implementations28 Jun 2021 Yuhao Liu, Jiake Xie, Yu Qiao, Yong Tang and, Xin Yang

Image matting is an ill-posed problem that aims to estimate the opacity of foreground pixels in an image.

Image Matting

Feature-Level Collaboration: Joint Unsupervised Learning of Optical Flow, Stereo Depth and Camera Motion

no code implementations CVPR 2021 Cheng Chi, Qingjie Wang, Tianyu Hao, Peng Guo, Xin Yang

In this paper, we show that effective feature-level collaboration of the networks for the three respective tasks could achieve much greater performance improvement for all three tasks than only loss-level joint optimization.

Depth And Camera Motion Motion Estimation +4

Depth-Aware Mirror Segmentation

no code implementations CVPR 2021 Haiyang Mei, Bo Dong, Wen Dong, Pieter Peers, Xin Yang, Qiang Zhang, Xiaopeng Wei

To exploit depth information in mirror segmentation, we first construct a large-scale RGB-D mirror segmentation dataset, which we subsequently employ to train a novel depth-aware mirror segmentation framework.

LENAS: Learning-based Neural Architecture Search and Ensemble for 3D Radiotherapy Dose Prediction

no code implementations12 Jun 2021 Yi Lin, Yanfei Liu, Hao Chen, Xin Yang, Kai Ma, Yefeng Zheng, Kwang-Ting Cheng

To the best of our knowledge, this is the first attempt to investigate NAS and knowledge distillation in ensemble learning, especially in the field of medical image analysis.

Ensemble Learning Knowledge Distillation +1

Joint Landmark and Structure Learning for Automatic Evaluation of Developmental Dysplasia of the Hip

no code implementations10 Jun 2021 Xindi Hu, LiMin Wang, Xin Yang, Xu Zhou, Wufeng Xue, Yan Cao, Shengfeng Liu, Yuhao Huang, Shuangping Guo, Ning Shang, Dong Ni, Ning Gu

In this study, we propose a multi-task framework to learn the relationships among landmarks and structures jointly and automatically evaluate DDH.

Vertical Federated Learning without Revealing Intersection Membership

no code implementations10 Jun 2021 Jiankai Sun, Xin Yang, Yuanshun Yao, Aonan Zhang, Weihao Gao, Junyuan Xie, Chong Wang

In this paper, we propose a vFL framework based on Private Set Union (PSU) that allows each party to keep sensitive membership information to itself.

Federated Learning

Deriving Autism Spectrum Disorder Functional Networks from RS-FMRI Data using Group ICA and Dictionary Learning

1 code implementation7 Jun 2021 Xin Yang, Ning Zhang, Donglin Wang

Fourth, we generate three corresponding masks based on the 20 selected ROIs from group ICA, the 20 ROIs selected from dictionary learning, and the 40 combined ROIs selected from both.

Dictionary Learning

FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis

no code implementations11 May 2021 Baihe Huang, Xiaoxiao Li, Zhao Song, Xin Yang

Nevertheless, training analysis of neural networks in FL is non-trivial for two reasons: first, the objective loss function we are optimizing is non-smooth and non-convex, and second, we are even not updating in the gradient direction.

Federated Learning

A Two-Stage Attentive Network for Single Image Super-Resolution

1 code implementation21 Apr 2021 Jiqing Zhang, Chengjiang Long, Yuxin Wang, Haiyin Piao, Haiyang Mei, Xin Yang, BaoCai Yin

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress.

Image Reconstruction Image Super-Resolution +1

Camouflaged Object Segmentation with Distraction Mining

1 code implementation CVPR 2021 Haiyang Mei, Ge-Peng Ji, Ziqi Wei, Xin Yang, Xiaopeng Wei, Deng-Ping Fan

In this paper, we strive to embrace challenges towards effective and efficient COS. To this end, we develop a bio-inspired framework, termed Positioning and Focus Network (PFNet), which mimics the process of predation in nature.

Camouflaged Object Segmentation Dichotomous Image Segmentation +1

Smart Scribbles for Image Mating

no code implementations31 Mar 2021 Xin Yang, Yu Qiao, Shaozhe Chen, Shengfeng He, BaoCai Yin, Qiang Zhang, Xiaopeng Wei, Rynson W. H. Lau

Image matting is an ill-posed problem that usually requires additional user input, such as trimaps or scribbles.

Image Matting

Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Text Balloon Generation

no code implementations26 Jan 2021 Xin Yang, Zongliang Ma, Letian Yu, Ying Cao, BaoCai Yin, Xiaopeng Wei, Qiang Zhang, Rynson W. H. Lau

Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios.

CPT: Efficient Deep Neural Network Training via Cyclic Precision

1 code implementation ICLR 2021 Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vikas Chandra, Yingyan Lin

In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training.

Language Modelling

Multi-scale Information Assembly for Image Matting

no code implementations7 Jan 2021 Yu Qiao, Yuhao Liu, Qiang Zhu, Xin Yang, Yuxin Wang, Qiang Zhang, Xiaopeng Wei

Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images.

Image Matting

Tripartite Information Mining and Integration for Image Matting

1 code implementation ICCV 2021 Yuhao Liu, Jiake Xie, Xiao Shi, Yu Qiao, Yujie Huang, Yong Tang, Xin Yang

Regarding the nature of image matting, most researches have focused on solutions for transition regions.

Image Matting

DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets

no code implementations13 Oct 2020 Shujun Wang, Lequan Yu, Kang Li, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng

Our DoFE framework dynamically enriches the image features with additional domain prior knowledge learned from multi-source domains to make the semantic features more discriminative.

Domain Generalization Image Segmentation +1

Weakly-supervised Salient Instance Detection

no code implementations29 Sep 2020 Xin Tian, Ke Xu, Xin Yang, Bao-Cai Yin, Rynson W. H. Lau

Inspired by this insight, we propose to use class and subitizing labels as weak supervision for the SID problem.

Boundary Detection Object Localization +1

Style-invariant Cardiac Image Segmentation with Test-time Augmentation

no code implementations24 Sep 2020 Xiaoqiong Huang, Zejian Chen, Xin Yang, Zhendong Liu, Yuxin Zou, Mingyuan Luo, Wufeng Xue, Dong Ni

Based on the zero-shot style transfer to remove appearance shift and test-time augmentation to explore diverse underlying anatomy, our proposed method is effective in combating the appearance shift.

Anatomy Cardiac Segmentation +3

Designing Neural Networks for Real-Time Systems

no code implementations26 Aug 2020 Hammond Pearce, Xin Yang, Partha S. Roop, Marc Katzef, Tórur Biskopstø Strøm

This issue stems largely from the implementation strategies used within common neural network frameworks -- their underlying source code is often simply unsuitable for formal techniques such as static timing analysis.

Computer-aided Tumor Diagnosis in Automated Breast Ultrasound using 3D Detection Network

no code implementations31 Jul 2020 Junxiong Yu, Chaoyu Chen, Xin Yang, Yi Wang, Dan Yan, Jianxing Zhang, Dong Ni

The efficacy of our network is verified from a collected dataset of 418 patients with 145 benign tumors and 273 malignant tumors.

Breast Cancer Detection Classification +1

TENet: Triple Excitation Network for Video Salient Object Detection

no code implementations ECCV 2020 Sucheng Ren, Chu Han, Xin Yang, Guoqiang Han, Shengfeng He

In this paper, we propose a simple yet effective approach, named Triple Excitation Network, to reinforce the training of video salient object detection (VSOD) from three aspects, spatial, temporal, and online excitations.

object-detection Salient Object Detection +1

Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes

1 code implementation28 Apr 2020 Xin Yang, Xu Wang, Yi Wang, Haoran Dou, Shengli Li, Huaxuan Wen, Yi Lin, Pheng-Ann Heng, Dong Ni

In this paper, we propose the first fully-automated solution to segment the whole fetal head in US volumes.

A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI

2 code implementations27 Apr 2020 Haoran Dou, Davood Karimi, Caitlin K. Rollins, Cynthia M. Ortinau, Lana Vasung, Clemente Velasco-Annis, Abdelhakim Ouaalam, Xin Yang, Dong Ni, Ali Gholipour

Automatic segmentation of the cortical plate, on the other hand, is challenged by the relatively low resolution of the reconstructed fetal brain MRI scans compared to the thin structure of the cortical plate, partial voluming, and the wide range of variations in the morphology of the cortical plate as the brain matures during gestation.

Sketching Transformed Matrices with Applications to Natural Language Processing

no code implementations23 Feb 2020 Yingyu Liang, Zhao Song, Mengdi Wang, Lin F. Yang, Xin Yang

We show that our approach obtains small error and is efficient in both space and time.

One-Shot Imitation Filming of Human Motion Videos

no code implementations23 Dec 2019 Chong Huang, Yuanjie Dang, Peng Chen, Xin Yang, Kwang-Ting, Cheng

Imitation learning has been applied to mimic the operation of a human cameraman in several autonomous cinematography systems.

Imitation Learning Style Transfer

Adaptive Densely Connected Super-Resolution Reconstruction

1 code implementation17 Dec 2019 Tangxin Xie, Xin Yang, Yu Jia, Chen Zhu, Xiaochuan Li

For a better performance in single image super-resolution(SISR), we present an image super-resolution algorithm based on adaptive dense connection (ADCSR).

Image Super-Resolution Single Image Super Resolution +1

Agent with Warm Start and Active Termination for Plane Localization in 3D Ultrasound

1 code implementation10 Oct 2019 Haoran Dou, Xin Yang, Jikuan Qian, Wufeng Xue, Hao Qin, Xu Wang, Lequan Yu, Shujun Wang, Yi Xiong, Pheng-Ann Heng, Dong Ni

In this study, we propose a novel reinforcement learning (RL) framework to automatically localize fetal brain standard planes in 3D US.

Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics

6 code implementations CVPR 2020 Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, Siwei Lyu

AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information.

DeepFake Detection Face Swapping

Total Least Squares Regression in Input Sparsity Time

1 code implementation NeurIPS 2019 Huaian Diao, Zhao Song, David P. Woodruff, Xin Yang

In the total least squares problem, one is given an $m \times n$ matrix $A$, and an $m \times d$ matrix $B$, and one seeks to "correct" both $A$ and $B$, obtaining matrices $\hat{A}$ and $\hat{B}$, so that there exists an $X$ satisfying the equation $\hat{A}X = \hat{B}$.

regression

Joint Segmentation and Landmark Localization of Fetal Femur in Ultrasound Volumes

no code implementations31 Aug 2019 Xu Wang, Xin Yang, Haoran Dou, Shengli Li, Pheng-Ann Heng, Dong Ni

In this paper, we propose an effective framework for simultaneous segmentation and landmark localization in prenatal ultrasound volumes.

Where Is My Mirror?

1 code implementation ICCV 2019 Xin Yang, Haiyang Mei, Ke Xu, Xiaopeng Wei, Bao-Cai Yin, Rynson W. H. Lau

To the best of our knowledge, this is the first work to address the mirror segmentation problem with a computational approach.

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.

Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound

1 code implementation3 Jul 2019 Yi Wang, Haoran Dou, Xiao-Wei Hu, Lei Zhu, Xin Yang, Ming Xu, Jing Qin, Pheng-Ann Heng, Tianfu Wang, Dong Ni

Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.

Image Segmentation Medical Image Segmentation +1

Boundary and Entropy-driven Adversarial Learning for Fundus Image Segmentation

1 code implementation26 Jun 2019 Shujun Wang, Lequan Yu, Kang Li, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng

The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions.

Image Segmentation Semantic Segmentation +1

Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound

no code implementations9 Jun 2019 Zhao Song, Xin Yang

We improve the over-parametrization size over two beautiful results [Li and Liang' 2018] and [Du, Zhai, Poczos and Singh' 2019] in deep learning theory.

Learning Theory

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset

2 code implementations CVPR 2019 Tianyu Wang, Xin Yang, Ke Xu, Shaozhe Chen, Qiang Zhang, Rynson Lau

Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner.

Single Image Deraining

Exposing GAN-synthesized Faces Using Landmark Locations

no code implementations30 Mar 2019 Xin Yang, Yuezun Li, Honggang Qi, Siwei Lyu

Generative adversary networks (GANs) have recently led to highly realistic image synthesis results.

General Classification Image Generation

Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image

no code implementations CVPR 2019 Xiaoguang Han, Zhaoxuan Zhang, Dong Du, Mingdai Yang, Jingming Yu, Pan Pan, Xin Yang, Ligang Liu, Zixiang Xiong, Shuguang Cui

Given a single depth image, our method first goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide to the next view inpainting step, which attempts to make up the missing information; the third step involves projecting the volume under the same view of the input, concatenating them to complete the current view depth, and integrating all depth into the point cloud.

Patch-based Output Space Adversarial Learning for Joint Optic Disc and Cup Segmentation

no code implementations20 Feb 2019 Shujun Wang, Lequan Yu, Xin Yang, Chi-Wing Fu, Pheng-Ann Heng

In this paper, we present a novel patchbased Output Space Adversarial Learning framework (pOSAL) to jointly and robustly segment the OD and OC from different fundus image datasets.

Unsupervised Domain Adaptation

Semi-supervised mp-MRI Data Synthesis with StitchLayer and Auxiliary Distance Maximization

no code implementations17 Dec 2018 Zhiwei Wang, Yi Lin, Kwang-Ting Cheng, Xin Yang

Experimental results show that our method can effectively synthesize a large variety of mpMRI images which contain meaningful CS PCa lesions, display a good visual quality and have the correct paired relationship.

Synthesizing Multi-Parameter Magnetic Resonance Imaging (Mp-Mri) Data

Deep Hierarchical Machine: a Flexible Divide-and-Conquer Architecture

no code implementations3 Dec 2018 Shichao Li, Xin Yang, Tim Cheng

We propose Deep Hierarchical Machine (DHM), a model inspired from the divide-and-conquer strategy while emphasizing representation learning ability and flexibility.

Face Alignment General Classification +3

Active Matting

no code implementations NeurIPS 2018 Xin Yang, Ke Xu, Shaozhe Chen, Shengfeng He, Baocai Yin Yin, Rynson Lau

Our aim is to discover the most informative sequence of regions for user input in order to produce a good alpha matte with minimum labeling efforts.

Image Matting

Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance

1 code implementation4 Nov 2018 Zechun Liu, Wenhan Luo, Baoyuan Wu, Xin Yang, Wei Liu, Kwang-Ting Cheng

To address the training difficulty, we propose a training algorithm using a tighter approximation to the derivative of the sign function, a magnitude-aware gradient for weight updating, a better initialization method, and a two-step scheme for training a deep network.

Depth Estimation

Exposing Deep Fakes Using Inconsistent Head Poses

1 code implementation1 Nov 2018 Xin Yang, Yuezun Li, Siwei Lyu

In this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes).

General Classification

Tool Breakage Detection using Deep Learning

no code implementations16 Aug 2018 Guang Li, Xin Yang, DuanBing Chen, Anxing Song, Yuke Fang, Junlin Zhou

In this work, we use the spindle current approach to detect the breakage of machine tools, which has the high performance of real-time monitoring, low cost, and easy to install.

Management

Active Object Reconstruction Using a Guided View Planner

no code implementations8 May 2018 Xin Yang, Yuanbo Wang, Yaru Wang, Bao-Cai Yin, Qiang Zhang, Xiaopeng Wei, Hongbo Fu

Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner.

Object Reconstruction

Neural Compatibility Modeling with Attentive Knowledge Distillation

no code implementations17 Apr 2018 Xuemeng Song, Fuli Feng, Xianjing Han, Xin Yang, Wei Liu, Liqiang Nie

Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching.

Knowledge Distillation speech-recognition +1

Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI

1 code implementation Elsevier 2017 Xin Yang, Chaoyue Liu, Zhiwei Wang, Jun Yang, Hung Le Min, Liang Wang, Kwang-Ting (Tim) Cheng

Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions’ locations.

General Classification

Time-Space Tradeoffs for Learning from Small Test Spaces: Learning Low Degree Polynomial Functions

no code implementations8 Aug 2017 Paul Beame, Shayan Oveis Gharan, Xin Yang

We develop an extension of recently developed methods for obtaining time-space tradeoff lower bounds for problems of learning from random test samples to handle the situation where the space of tests is signficantly smaller than the space of inputs, a class of learning problems that is not handled by prior work.

Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets

2 code implementations2 Aug 2017 Lequan Yu, Jie-Zhi Cheng, Qi Dou, Xin Yang, Hao Chen, Jing Qin, Pheng-Ann Heng

Second, it avoids learning redundant feature maps by encouraging feature reuse and hence requires fewer parameters to achieve high performance, which is essential for medical applications with limited training data.

Fine-grained Recurrent Neural Networks for Automatic Prostate Segmentation in Ultrasound Images

no code implementations6 Dec 2016 Xin Yang, Lequan Yu, Lingyun Wu, Yi Wang, Dong Ni, Jing Qin, Pheng-Ann Heng

Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.

Image Segmentation Medical Image Segmentation +1

Concept based Attention

no code implementations11 May 2016 Jie You, Xin Yang, Matthias Hub

Attention endows animals an ability to concentrate on the most relevant information among a deluge of distractors at any given time, either through volitionally 'top-down' biasing, or driven by automatically 'bottom-up' saliency of stimuli, in favour of advantageous competition in neural modulations for information processing.

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