Search Results for author: Yi Wang

Found 128 papers, 39 papers with code

DoTAT: A Domain-oriented Text Annotation Tool

1 code implementation ACL 2022 Yupian Lin, Tong Ruan, Ming Liang, Tingting Cai, Wen Du, Yi Wang

Secondly, the tool provides annotation of events, nested event and nested entity, which are frequently required in domain-related text structuring tasks.

text annotation

Chinese Grammatical Error Correction Based on Hybrid Models with Data Augmentation

no code implementations AACL (NLP-TEA) 2020 Yi Wang, Ruibin Yuan, Yan‘gen Luo, Yufang Qin, NianYong Zhu, Peng Cheng, Lihuan Wang

A better Chinese Grammatical Error Diagnosis (CGED) system for automatic Grammatical Error Correction (GEC) can benefit foreign Chinese learners and lower Chinese learning barriers.

Data Augmentation Grammatical Error Correction

Rate-Perception Optimized Preprocessing for Video Coding

no code implementations25 Jan 2023 Chengqian Ma, Zhiqiang Wu, Chunlei Cai, Pengwei Zhang, Yi Wang, Long Zheng, Chao Chen, Quan Zhou

In the past decades, lots of progress have been done in the video compression field including traditional video codec and learning-based video codec.

Image Quality Assessment Video Compression

Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision

no code implementations22 Jan 2023 Jilan Xu, Junlin Hou, Yuejie Zhang, Rui Feng, Yi Wang, Yu Qiao, Weidi Xie

The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities.

Semantic Segmentation

A Survey of Face Recognition

no code implementations26 Dec 2022 Xinyi Wang, Jianteng Peng, Sufang Zhang, Bihui Chen, Yi Wang, Yandong Guo

Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks.

Face Recognition

InternVideo: General Video Foundation Models via Generative and Discriminative Learning

1 code implementation6 Dec 2022 Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, Sen Xing, Guo Chen, Junting Pan, Jiashuo Yu, Yali Wang, LiMin Wang, Yu Qiao

Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications.

 Ranked #1 on Video Retrieval on DiDeMo (using extra training data)

Action Classification Contrastive Learning +6

Noisy Label Detection for Speaker Recognition

1 code implementation1 Dec 2022 Ruibin Yuan, Hanzhi Yin, Yi Wang, Yifan He, Yushi Ye, Lei Zhang

The success of deep neural networks requires both high annotation quality and massive data.

Metric Learning Speaker Recognition +1

NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views

no code implementations29 Nov 2022 Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Yi Wang, Zhangyang Wang

In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360{\deg} views that correspond well with the given reference image.

Denoising Depth Estimation

A Particle-based Sparse Gaussian Process Optimizer

no code implementations26 Nov 2022 Chandrajit Bajaj, Omatharv Bharat Vaidya, Yi Wang

Task learning in neural networks typically requires finding a globally optimal minimizer to a loss function objective.

Image Classification

CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors

no code implementations26 Nov 2022 Junlin Hou, Jilan Xu, Nan Zhang, Yi Wang, Yuejie Zhang, Xiaobo Zhang, Rui Feng

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on Computer Vision (ECCV 2022).

COVID-19 Diagnosis Representation Learning

Adjacent Slice Feature Guided 2.5D Network for Pulmonary Nodule Segmentation

no code implementations19 Nov 2022 Xinwei Xue, Gaoyu Wang, Long Ma, Qi Jia, Yi Wang

In this paper, we design an adjacent slice feature fusion model to introduce information from adjacent slices.

UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

1 code implementation17 Nov 2022 Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, LiMin Wang, Yu Qiao

UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format.

Video Understanding

LARO: Learned Acquisition and Reconstruction Optimization to accelerate Quantitative Susceptibility Mapping

1 code implementation1 Nov 2022 Jinwei Zhang, Pascal Spincemaille, Hang Zhang, Thanh D. Nguyen, Chao Li, Jiahao Li, Ilhami Kovanlikaya, Mert R. Sabuncu, Yi Wang

In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM.

Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection

no code implementations29 Oct 2022 Yi Wang, Jiajun Deng, Tianzi Wang, Bo Zheng, Shoukang Hu, Xunying Liu, Helen Meng

However, PLM domain fine-tuning is commonly based on the masked word or sentence prediction costs that are inconsistent with the back-end AD detection task.

alzheimer's disease detection

Non-Iterative Scribble-Supervised Learning with Pacing Pseudo-Masks for Medical Image Segmentation

no code implementations20 Oct 2022 Zefan Yang, Di Lin, Dong Ni, Yi Wang

To address these issues, we propose a non-iterative method where a stream of varying (pacing) pseudo-masks teach a network via consistency training, named PacingPseudo.

Image Segmentation Medical Image Segmentation +1

EarthNets: Empowering AI in Earth Observation

no code implementations10 Oct 2022 Zhitong Xiong, Fahong Zhang, Yi Wang, Yilei Shi, Xiao Xiang Zhu

Furthermore, a new platform for Earth observation, termed EarthNets, is released as a means of achieving a fair and consistent evaluation of deep learning methods on remote sensing data.

Scene Understanding Weather Forecasting

Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?

2 code implementations15 Sep 2022 Yi Wang, Zhiwen Fan, Tianlong Chen, Hehe Fan, Zhangyang Wang

Vision Transformers (ViTs) have proven to be effective, in solving 2D image understanding tasks by training over large-scale image datasets; and meanwhile as a somehow separate track, in modeling the 3D visual world too such as voxels or point clouds.

Point Cloud Segmentation

A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans

no code implementations8 Sep 2022 Zeyu Liu, Yi Wang, Jing Wen, Yong Zhang, Hao Yin, Chao Guo, Zhongyu Wang

In addition, in order to improve the segmentation performance, we adopt multi-view and multi-window level method, at the same time we employ a fine-tune strategy to mitigate the impact of inconsistent labeling.

PulseDL-II: A System-on-Chip Neural Network Accelerator for Timing and Energy Extraction of Nuclear Detector Signals

no code implementations2 Sep 2022 Pengcheng Ai, Zhi Deng, Yi Wang, Hui Gong, Xinchi Ran, Zijian Lang

Simulations and experiments demonstrate the satisfactory accuracy and additional benefits of neural networks in this area.


Quality-Constant Per-Shot Encoding by Two-Pass Learning-based Rate Factor Prediction

no code implementations23 Aug 2022 Chunlei Cai, Yi Wang, Xiaobo Li, Tianxiao Ye

With the help of first pass predicted RF and corresponding actual quality as feedback, the second pass prediction will be highly accurate.

Parameter Prediction

Self-supervised Learning in Remote Sensing: A Review

1 code implementation27 Jun 2022 Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Lichao Mou, Xiao Xiang Zhu

In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities.

Multi-Label Image Classification Self-Supervised Learning

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)

no code implementations23 Jun 2022 Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao

Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller.

Data Augmentation Vision and Language Navigation

WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis

no code implementations20 Jun 2022 Yi Wang, Yi Si

Recently, GAN-based neural vocoders such as Parallel WaveGAN, MelGAN, HiFiGAN, and UnivNet have become popular due to their lightweight and parallel structure, resulting in a real-time synthesized waveform with high fidelity, even on a CPU.

Speech Synthesis

Monitoring Urban Forests from Auto-Generated Segmentation Maps

no code implementations14 Jun 2022 Conrad M Albrecht, Chenying Liu, Yi Wang, Levente Klein, Xiao Xiang Zhu

We present and evaluate a weakly-supervised methodology to quantify the spatio-temporal distribution of urban forests based on remotely sensed data with close-to-zero human interaction.

Semantic Segmentation

UMSNet: An Universal Multi-sensor Network for Human Activity Recognition

no code implementations24 May 2022 Jialiang Wang, Haotian Wei, Yi Wang, Shu Yang, Chi Li

Human activity recognition (HAR) based on multimodal sensors has become a rapidly growing branch of biometric recognition and artificial intelligence.

Human Activity Recognition Time Series Classification

Beam Training and Tracking in MmWave Communication: A Survey

no code implementations20 May 2022 Yi Wang, Zhiqing Wei, Zhiyong Feng

This article provides an overview of the beam training and tracking technologies on mmWave bands and reveals the insights for future research in the 6th Generation (6G) mobile network.

Long-run User Value Optimization in Recommender Systems through Content Creation Modeling

no code implementations25 Apr 2022 Akos Lada, Xiaoxuan Liu, Jens Rischbieth, Yi Wang, Yuwen Zhang

Content recommender systems are generally adept at maximizing immediate user satisfaction but to optimize for the \textit{long-run} user value, we need more statistically sophisticated solutions than off-the-shelf simple recommender algorithms.

BIG-bench Machine Learning Recommendation Systems

Self-supervised Vision Transformers for Joint SAR-optical Representation Learning

1 code implementation11 Apr 2022 Yi Wang, Conrad M Albrecht, Xiao Xiang Zhu

Experimental results employing the BigEarthNet-MM dataset demonstrate the benefits of both, the ViT backbones and the proposed multimodal SSL algorithm DINO-MM.

Data Augmentation Representation Learning +1

A Global Modeling Approach for Load Forecasting in Distribution Networks

no code implementations1 Apr 2022 Miha Grabner, Yi Wang, Qingsong Wen, Boštjan Blažič, Vitomir Štruc

Efficient load forecasting is needed to ensure better observability in the distribution networks, whereas such forecasting is made possible by an increasing number of smart meter installations.

Load Forecasting

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

1 code implementation CVPR 2022 Wenbo Li, Zhe Lin, Kun Zhou, Lu Qi, Yi Wang, Jiaya Jia

Recent studies have shown the importance of modeling long-range interactions in the inpainting problem.

Image Inpainting

Hilbert Flattening: a Locality-Preserving Matrix Unfolding Method

no code implementations21 Feb 2022 Qingsong Zhao, Zhipeng Zhou, Yi Wang, Yu Qiao, Cairong Zhao

Zigzag flattening (ZF) is commonly utilized as a default option to get the image patches ordering in deep models, e. g. vision transformers (ViTs).

TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting

1 code implementation17 Feb 2022 Haihan Tang, Yi Wang, Lap-Pui Chau

Specifically, TAFNet is divided into one main stream and two auxiliary streams.

Crowd Counting

Robust Anomaly Detection for Time-series Data

no code implementations6 Feb 2022 Min Hu, Yi Wang, Xiaowei Feng, Shengchen Zhou, Zhaoyu Wu, Yuan Qin

The experiments showed that in benchmark datasets RADTD possessed higher accuracy and robustness than recurrence qualification analysis and extreme learning machine autoencoder, respectively, and that RADTD accurately detected the occurrence of tunneling settlement accidents, indicating its remarkable performance in accuracy and robustness.

Anomaly Detection Time Series Anomaly Detection

Recurrent Feature Propagation and Edge Skip-Connections for Automatic Abdominal Organ Segmentation

no code implementations2 Jan 2022 Zefan Yang, Di Lin, Yi Wang

Automatic segmentation of abdominal organs in computed tomography (CT) images can support radiation therapy and image-guided surgery workflows.

Computed Tomography (CT) Semantic Segmentation

Make A Long Image Short: Adaptive Token Length for Vision Transformers

no code implementations3 Dec 2021 Yichen Zhu, Yuqin Zhu, Jie Du, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference.

Action Recognition Image Classification

Training BatchNorm Only in Neural Architecture Search and Beyond

no code implementations1 Dec 2021 Yichen Zhu, Jie Du, Yuqin Zhu, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet.

Fairness Neural Architecture Search

Reinforcement Learning of Self Enhancing Camera Image and Signal Processing

1 code implementation15 Nov 2021 Chandrajit Bajaj, Yi Wang, Yunhao Yang

Our \textit{Recursive Self Enhancement Reinforcement Learning}(RSE-RL) model views the identification and correction of artifacts as a recursive self-learning and self-improvement exercise and consists of two major sub-modules: (i) The latent feature sub-space clustering/grouping obtained through variational auto-encoders enabling rapid identification of the correspondence and discrepancy between noisy and clean image patches.

Data Augmentation Image Enhancement +3

Learning Ultrasound Scanning Skills from Human Demonstrations

no code implementations9 Nov 2021 Xutian Deng, Ziwei Lei, Yi Wang, Miao Li

Finally, the robustness of the proposed framework is validated with the experiments on real data from sonographers.

Nonlinear ICA Using Volume-Preserving Transformations

no code implementations ICLR 2022 Xiaojiang Yang, Yi Wang, Jiacheng Sun, Xing Zhang, Shifeng Zhang, Zhenguo Li, Junchi Yan

Nonlinear ICA is a fundamental problem in machine learning, aiming to identify the underlying independent components (sources) from data which is assumed to be a nonlinear function (mixing function) of these sources.

Image Synthesis via Semantic Composition

no code implementations ICCV 2021 Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia

In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts.

Image Generation Semantic Composition

Conditional Temporal Variational AutoEncoder for Action Video Prediction

no code implementations12 Aug 2021 Xiaogang Xu, Yi Wang, LiWei Wang, Bei Yu, Jiaya Jia

To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.

motion prediction Video Prediction

Open-World Entity Segmentation

2 code implementations29 Jul 2021 Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia

By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality.

Image Manipulation Image Segmentation +1

Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification

no code implementations17 Jul 2021 Lisha Tang, Yi Wang, Lap-Pui Chau

Current part-level feature learning methods typically detect vehicle parts via uniform division, outside tools, or attention modeling.

Vehicle Re-Identification

Cost-Oriented Load Forecasting

no code implementations5 Jul 2021 Jialun Zhang, Yi Wang, Gabriela Hug

Accurate load prediction is an effective way to reduce power system operation costs.

Load Forecasting

FedNILM: Applying Federated Learning to NILM Applications at the Edge

no code implementations7 Jun 2021 Yu Zhang, Guoming Tang, Qianyi Huang, Yi Wang, Xudong Wang, Jiadong Lou

Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring.

Federated Learning Model Compression +3

More Behind Your Electricity Bill: a Dual-DNN Approach to Non-Intrusive Load Monitoring

no code implementations1 Jun 2021 Yu Zhang, Guoming Tang, Qianyi Huang, Yi Wang, Hong Xu

Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances.

Non-Intrusive Load Monitoring

Multi-object Tracking with Tracked Object Bounding Box Association

1 code implementation17 May 2021 Nanyang Yang, Yi Wang, Lap-Pui Chau

The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network.

Association Multi-Object Tracking

Solve routing problems with a residual edge-graph attention neural network

1 code implementation6 May 2021 Kun Lei, Peng Guo, Yi Wang, Xiao Wu, Wenchao Zhao

In this paper, an end-to-end deep reinforcement learning framework is proposed to solve this type of combinatorial optimization problems.

Combinatorial Optimization Graph Attention +1

Moving Towards Centers: Re-ranking with Attention and Memory for Re-identification

no code implementations4 May 2021 Yunhao Zhou, Yi Wang, Lap-Pui Chau

Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serving as discriminative combination weights.

Re-Ranking Retrieval +1

Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network

no code implementations4 May 2021 Chao Li, Hang Zhang, Jinwei Zhang, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed.

Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization

1 code implementation26 Apr 2021 Yi Wang, Xinyu Hou, Lap-Pui Chau

In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet.

Crowd Counting

Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors

1 code implementation22 Apr 2021 Arman Maesumi, Mingkang Zhu, Yi Wang, Tianlong Chen, Zhangyang Wang, Chandrajit Bajaj

This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes.

Adversarial Attack

Machine-learned 3D Building Vectorization from Satellite Imagery

no code implementations13 Apr 2021 Yi Wang, Stefano Zorzi, Ksenia Bittner

We propose a machine learning based approach for automatic 3D building reconstruction and vectorization.

Semantic Segmentation

Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing

1 code implementation1 Apr 2021 Yunhao Yang, Yuhan Zheng, Yi Wang, Chandrajit Bajaj

Rather, PSL-AE first diagnostically encodes patches extracted from noisy and clean image pairs, with different artifact type and distortion levels, by contrastive learning.

Contrastive Learning Image Denoising

Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction

no code implementations10 Mar 2021 Jinwei Zhang, Hang Zhang, Chao Li, Pascal Spincemaille, Mert Sabuncu, Thanh D. Nguyen, Yi Wang

Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging.

Image Reconstruction

Prevalent Behavior of Smooth Strongly Monotone Discrete-Time Dynamical Systems

no code implementations8 Mar 2021 Yi Wang, Jinxiang Yao, Yufeng Zhang

For C1-smooth strongly monotone discrete-time dynamical systems, it is shown that ``convergence to linearly stable cycles" is a prevalent asymptotic behavior in the measuretheoretic sense.

Dynamical Systems

NeRD: Neural Representation of Distribution for Medical Image Segmentation

no code implementations6 Mar 2021 Hang Zhang, Rongguang Wang, Jinwei Zhang, Chao Li, Gufeng Yang, Pascal Spincemaille, Thanh Nguyen, Yi Wang

We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution.

Image Segmentation Lesion Segmentation +1

A Comprehensive Review of Deep Learning-based Single Image Super-resolution

no code implementations18 Feb 2021 Syed Muhammad Arsalan Bashir, Yi Wang, Mahrukh Khan, Yilong Niu

This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution.

Image Super-Resolution Single Image Super Resolution

The Yamabe flow on asymptotically flat manifolds

no code implementations15 Feb 2021 Eric Chen, Yi Wang

We study the Yamabe flow starting from an asymptotically flat manifold $(M^n, g_0)$.

Differential Geometry Analysis of PDEs 53C18, 53Exx

Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher

no code implementations ICCV 2021 Yichen Zhu, Yi Wang

We formulate the knowledge distillation as a multi-task learning problem so that the teacher transfers knowledge to the student only if the student can benefit from learning such knowledge.

Knowledge Distillation Multi-Task Learning +3

SEGSys: A mapping system for segmentation analysis in energy

no code implementations11 Dec 2020 Xiufeng Liu, Rongling Li, Yi Wang, Per Sieverts Nielsen

This paper showcases the system on the segmentation analysis using an electricity consumption data set and validates the effectiveness of the system.


Enhance Convolutional Neural Networks with Noise Incentive Block

no code implementations9 Dec 2020 Menghan Xia, Yi Wang, Chu Han, Tien-Tsin Wong

Noise Incentive Block (NIB), which serves as a generic plug-in for any CNN generation model.

Image Generation Translation

RANet: Region Attention Network for Semantic Segmentation

1 code implementation NeurIPS 2020 Dingguo Shen, Yuanfeng Ji, Ping Li, Yi Wang, Di Lin

In contrast to the previous methods, RANet configures the information pathways between the pixels in different regions, enabling the region interaction to exchange the regional context for enhancing all of the pixels in the image.

Semantic Segmentation

Rethinking and Designing a High-performing Automatic License Plate Recognition Approach

no code implementations30 Nov 2020 Yi Wang, Zhen-Peng Bian, Yunhao Zhou, Lap-Pui Chau

Our study illustrates the outstanding design of ALPR with four insights: (1) the resampling-based cascaded framework is beneficial to both speed and accuracy; (2) the highly efficient license plate recognition should abundant additional character segmentation and recurrent neural network (RNN), but adopt a plain convolutional neural network (CNN); (3) in the case of CNN, taking advantage of vertex information on license plates improves the recognition performance; and (4) the weight-sharing character classifier addresses the lack of training images in small-scale datasets.

Data Augmentation License Plate Detection +1

Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020

no code implementations20 Oct 2020 Shufan Shen, Ran Miao, Yi Wang, Zhihua Wei

In this report, we discribe the submission of Tongji University undergraduate team to the CLOSE track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020 at Interspeech 2020.

Data Augmentation Denoising +2

Ensembling Low Precision Models for Binary Biomedical Image Segmentation

no code implementations16 Oct 2020 Tianyu Ma, Hang Zhang, Hanley Ong, Amar Vora, Thanh D. Nguyen, Ajay Gupta, Yi Wang, Mert Sabuncu

Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent.

Image Segmentation Lesion Segmentation +2

Assessing Lesion Segmentation Bias of Neural Networks on Motion Corrupted Brain MRI

no code implementations12 Oct 2020 Tejas Sudharshan Mathai, Yi Wang, Nathan Cross

In this paper, we seek to quantify the bias in terms of the impact that different levels of motion artifacts have on the performance of neural networks engaged in a lesion segmentation task.

Lesion Segmentation

Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

no code implementations29 Sep 2020 Hang Zhang, Jinwei Zhang, Rongguang Wang, Qihao Zhang, Susan A. Gauthier, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

Multiple sclerosis (MS) lesions occupy a small fraction of the brain volume, and are heterogeneous with regards to shape, size and locations, which poses a great challenge for training deep learning based segmentation models.

Lesion Segmentation

Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation

no code implementations13 Sep 2020 Hang Zhang, Jinwei Zhang, Rongguang Wang, Qihao Zhang, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed to capture global contextual information for performance enhancement.

Image Reconstruction Lesion Segmentation

Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping

no code implementations7 Sep 2020 Jinwei Zhang, Hang Zhang, Mert Sabuncu, Pascal Spincemaille, Thanh Nguyen, Yi Wang

A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation.

Density Estimation

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

Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI

no code implementations28 Jul 2020 Jinwei Zhang, Hang Zhang, Alan Wang, Qihao Zhang, Mert Sabuncu, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

The previously established LOUPE (Learning-based Optimization of the Under-sampling Pattern) framework for optimizing the k-space sampling pattern in MRI was extended in three folds: firstly, fully sampled multi-coil k-space data from the scanner, rather than simulated k-space data from magnitude MR images in LOUPE, was retrospectively under-sampled to optimize the under-sampling pattern of in-vivo k-space data; secondly, binary stochastic k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator to estimate the gradient of the threshold operation in a neural network; thirdly, modified unrolled optimization network, rather than modified U-Net in LOUPE, was used as the reconstruction network in order to reconstruct multi-coil data properly and reduce the dependency on training data.

A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds

2 code implementations25 Jul 2020 Yi Wang, Junhui Hou, Xinyu Hou, Lap-Pui Chau

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i. e., objects are labeled with points) to estimate both the center points and sizes of crowded objects.

Crowd Counting object-detection +1

Cache-enabling UAV Communications: Network Deployment and Resource Allocation

no code implementations22 Jul 2020 Tiankui Zhang, Yi Wang, Yuanwei Liu, Wenjun Xu, Arumugam Nallanathan

We formulate a joint optimization problem of UAV deployment, caching placement and user association for maximizing QoE of users, which is evaluated by mean opinion score (MOS).


Can 3D Adversarial Logos Cloak Humans?

1 code implementation25 Jun 2020 Yi Wang, Jingyang Zhou, Tianlong Chen, Sijia Liu, Shiyu Chang, Chandrajit Bajaj, Zhangyang Wang

Contrary to the traditional adversarial patch, this new form of attack is mapped into the 3D object world and back-propagates to the 2D image domain through differentiable rendering.

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.

When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks

no code implementations19 Apr 2020 Zhiyu Zhu, Zhen-Peng Bian, Junhui Hou, Yi Wang, Lap-Pui Chau

However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters.

Neural Architecture Search

Attentive Normalization for Conditional Image Generation

1 code implementation CVPR 2020 Yi Wang, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.

Conditional Image Generation Semantic correspondence +2

VCNet: A Robust Approach to Blind Image Inpainting

2 code implementations ECCV 2020 Yi Wang, Ying-Cong Chen, Xin Tao, Jiaya Jia

Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image.

Image Inpainting

PointINS: Point-based Instance Segmentation

no code implementations13 Mar 2020 Lu Qi, Yi Wang, Yukang Chen, Yingcong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia

In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.

Instance Segmentation Object Detection +2

Convolutional Neural Networks with Dynamic Regularization

no code implementations26 Sep 2019 Yi Wang, Zhen-Peng Bian, Junhui Hou, Lap-Pui Chau

That is, the regularization strength is fixed to a predefined schedule, and manual adjustments are required to adapt to various network architectures.

Bridging Commonsense Reasoning and Probabilistic Planning via a Probabilistic Action Language

no code implementations31 Jul 2019 Yi Wang, Shiqi Zhang, Joohyung Lee

In this paper, we present a unified framework to integrate icorpp's reasoning and planning components.

Decision Making

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

Fully Decoupled Neural Network Learning Using Delayed Gradients

1 code implementation21 Jun 2019 Huiping Zhuang, Yi Wang, Qinglai Liu, Shuai Zhang, Zhiping Lin

Training neural networks with back-propagation (BP) requires a sequential passing of activations and gradients, which forces the network modules to work in a synchronous fashion.

Wide-Context Semantic Image Extrapolation

2 code implementations CVPR 2019 Yi Wang, Xin Tao, Xiaoyong Shen, Jiaya Jia

This paper studies the fundamental problem of extrapolating visual context using deep generative models, i. e., extending image borders with plausible structure and details.

Image Inpainting Image Outpainting +1

Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language pBC+

no code implementations1 Apr 2019 Yi Wang, Joohyung Lee

Alternatively, the semantics of pBC+ can also be defined in terms of Markov Decision Process (MDP), which in turn allows for representing MDP in a succinct and elaboration tolerant way as well as to leverage an MDP solver to compute pBC+.

Understanding and Comparing Scalable Gaussian Process Regression for Big Data

no code implementations3 Nov 2018 Haitao Liu, Jianfei Cai, Yew-Soon Ong, Yi Wang

This paper devotes to investigating the methodological characteristics and performance of representative global and local scalable GPs including sparse approximations and local aggregations from four main perspectives: scalability, capability, controllability and robustness.


Weight Learning in a Probabilistic Extension of Answer Set Programs

no code implementations14 Aug 2018 Joohyung Lee, Yi Wang

Learning in LPMLN is in accordance with the stable model semantics, thereby it learns parameters for probabilistic extensions of knowledge-rich domains where answer set programming has shown to be useful but limited to the deterministic case, such as reachability analysis and reasoning about actions in dynamic domains.

The conditional permutation test for independence while controlling for confounders

no code implementations14 Jul 2018 Thomas B. Berrett, Yi Wang, Rina Foygel Barber, Richard J. Samworth

Like the conditional randomization test of Cand\`es et al. (2018), our test relies on the availability of an approximation to the distribution of $X \mid Z$.

Methodology Statistics Theory Statistics Theory

Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression

1 code implementation ICML 2018 Haitao Liu, Jianfei Cai, Yi Wang, Yew-Soon Ong

In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts.

Distributed Computing regression

A Probabilistic Extension of Action Language BC+

no code implementations2 May 2018 Joohyung Lee, Yi Wang

We present a probabilistic extension of action language BC+.

Scale-recurrent Network for Deep Image Deblurring

4 code implementations CVPR 2018 Xin Tao, Hongyun Gao, Yi Wang, Xiaoyong Shen, Jue Wang, Jiaya Jia

In single image deblurring, the "coarse-to-fine" scheme, i. e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches.

Ranked #3 on Image Deblurring on GoPro (Params (M) metric, using extra training data)

Deblurring Image Deblurring +1

Online Robust Image Alignment via Subspace Learning From Gradient Orientations

no code implementations ICCV 2017 Qingqing Zheng, Yi Wang, Pheng-Ann Heng

The proposed method integrates the subspace learning, transformed IGO reconstruction and image alignment into a unified online framework, which is robust for aligning images with severe intensity distortions.

Face Recognition

Computing LPMLN Using ASP and MLN Solvers

no code implementations19 Jul 2017 Joohyung Lee, Samidh Talsania, Yi Wang

LPMLN is a recent addition to probabilistic logic programming languages.

Incremental Kernel Null Space Discriminant Analysis for Novelty Detection

no code implementations CVPR 2017 Juncheng Liu, Zhouhui Lian, Yi Wang, Jianguo Xiao

This validates the superiority of our IKNDA against the state of the art in novelty detection for large-scale 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

On the Semantic Relationship between Probabilistic Soft Logic and Markov Logic

no code implementations28 Jun 2016 Joohyung Lee, Yi Wang

Markov Logic Networks (MLN) and Probabilistic Soft Logic (PSL) are widely applied formalisms in Statistical Relational Learning, an emerging area in Artificial Intelligence that is concerned with combining logical and statistical AI.

Relational Reasoning

Stochastic Patching Process

no code implementations23 May 2016 Xuhui Fan, Bin Li, Yi Wang, Yang Wang, Fang Chen

Due to constraints of partition strategy, existing models may cause unnecessary dissections in sparse regions when fitting data in dense regions.

Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problem

no code implementations22 May 2016 Peng Guo, Wenming Cheng, Yi Wang

This paper considers the two-stage capacitated facility location problem (TSCFLP) in which products manufactured in plants are delivered to customers via storage depots.

Consistency Analysis of Nearest Subspace Classifier

no code implementations24 Jan 2015 Yi Wang

The Nearest subspace classifier (NSS) finds an estimation of the underlying subspace within each class and assigns data points to the class that corresponds to its nearest subspace.

General Classification

Random Bits Regression: a Strong General Predictor for Big Data

no code implementations13 Jan 2015 Yi Wang, Yi Li, Momiao Xiong, Li Jin

To improve accuracy and speed of regressions and classifications, we present a data-based prediction method, Random Bits Regression (RBR).

BIG-bench Machine Learning regression

Maximum mutual information regularized classification

no code implementations27 Sep 2014 Jim Jing-Yan Wang, Yi Wang, Shiguang Zhao, Xin Gao

In this paper, a novel pattern classification approach is proposed by regularizing the classifier learning to maximize mutual information between the classification response and the true class label.

Classification General Classification

Tensity Research Based on the Information of Eye Movement

no code implementations17 Sep 2014 Yi Wang

User's mental state is concerned gradually, during the interaction course of human robot.

Stable Learning in Coding Space for Multi-Class Decoding and Its Extension for Multi-Class Hypothesis Transfer Learning

no code implementations CVPR 2014 Bang Zhang, Yi Wang, Yang Wang, Fang Chen

Many prevalent multi-class classification approaches can be unified and generalized by the output coding framework which usually consists of three phases: (1) coding, (2) learning binary classifiers, and (3) decoding.

General Classification Multi-class Classification +1

Latent Tree Models and Approximate Inference in Bayesian Networks

no code implementations15 Jan 2014 Yi Wang, Nevin L. Zhang, Tao Chen

We propose a novel method for approximate inference in Bayesian networks (BNs).

Exploration in Interactive Personalized Music Recommendation: A Reinforcement Learning Approach

no code implementations6 Nov 2013 Xinxi Wang, Yi Wang, David Hsu, Ye Wang

Current music recommender systems typically act in a greedy fashion by recommending songs with the highest user ratings.

Bayesian Inference Music Recommendation +4

MathGR: a tensor and GR computation package to keep it simple

1 code implementation6 Jun 2013 Yi Wang

We introduce the MathGR package, written in Mathematica.

Mathematical Software Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Theory Computational Physics

Monte Carlo Bayesian Reinforcement Learning

no code implementations27 Jun 2012 Yi Wang, Kok Sung Won, David Hsu, Wee Sun Lee

Bayesian reinforcement learning (BRL) encodes prior knowledge of the world in a model and represents uncertainty in model parameters by maintaining a probability distribution over them.

reinforcement-learning reinforcement Learning

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