Search Results for author: Chen Chen

Found 171 papers, 52 papers with code

SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection

1 code implementation6 Jan 2022 Chen Chen, Zhe Chen, Jing Zhang, DaCheng Tao

We observe that the prevailing set abstraction design for down-sampling points may maintain too much unimportant background information that can affect feature learning for detecting objects.

3D Object Detection

Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition

1 code implementation AAAI 2022 2021 Yue He, Chen Chen, Jing Zhang, Juhua Liu, Fengxiang He, Chaoyue Wang, Bo Du

Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.

 Ranked #1 on Scene Text Recognition on IIIT5k (using extra training data)

Graph Convolutional Network Language Modelling +1

A Practical Data-Free Approach to One-shot Federated Learning with Heterogeneity

no code implementations23 Dec 2021 Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Jianghe Xu, Shouhong Ding, Chao Wu

To the best of our knowledge, FedSyn is the first method that can be practically applied to various real-world applications due to the following advantages: (1) FedSyn requires no additional information (except the model parameters) to be transferred between clients and the server; (2) FedSyn does not require any auxiliary dataset for training; (3) FedSyn is the first to consider both model and statistical heterogeneities in FL, i. e., the clients' data are non-iid and different clients may have different model architectures.

Federated Learning

Creativity of AI: Automatic Symbolic Option Discovery for Facilitating Deep Reinforcement Learning

no code implementations18 Dec 2021 Mu Jin, Zhihao Ma, Kebing Jin, Hankz Hankui Zhuo, Chen Chen, Chao Yu

Despite of achieving great success in real life, Deep Reinforcement Learning (DRL) is still suffering from three critical issues, which are data efficiency, lack of the interpretability and transferability.

Montezuma's Revenge

Hierarchical Stochastic Scheduling of Multi-Community Integrated Energy Systems in Uncertain Environments via Stackelberg Game

no code implementations14 Dec 2021 Yang Li, Bin Wang, Zhen Yang, Jiazheng Li, Chen Chen

An operating entity utilizing community-integrated energy systems with a large number of small-scale distributed energy sources can easily trade with existing distribution markets.

A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems

no code implementations5 Dec 2021 Yang Li, Meng Zhang, Chen Chen

Facing the difficulty of expensive and trivial data collection and annotation, how to make a deep learning-based short-term voltage stability assessment (STVSA) model work well on a small training dataset is a challenging and urgent problem.

Data Augmentation

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

no code implementations28 Nov 2021 Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen

To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.

Federated Learning

Learning Debiased Models with Dynamic Gradient Alignment and Bias-conflicting Sample Mining

no code implementations25 Nov 2021 Bowen Zhao, Chen Chen, Qi Ju, Shutao Xia

Deep neural networks notoriously suffer from dataset biases which are detrimental to model robustness, generalization and fairness.


Causality-inspired Single-source Domain Generalization for Medical Image Segmentation

no code implementations24 Nov 2021 Cheng Ouyang, Chen Chen, Surui Li, Zeju Li, Chen Qin, Wenjia Bai, Daniel Rueckert

In this work, we investigate the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data is only available from one source domain, which is common in medical imaging applications.

Data Augmentation Domain Generalization +1

A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose

no code implementations24 Nov 2021 Ce Zheng, Matias Mendieta, Pu Wang, Aidong Lu, Chen Chen

We propose a pose analysis module that uses graph transformers to exploit structured and implicit joint correlations, and a mesh regression module that combines the extracted pose feature with the mesh template to reconstruct the final human mesh.

Virtual Try-on

Boost Distribution System Restoration with Emergency Communication Vehicles Considering Cyber-Physical Interdependence

no code implementations19 Nov 2021 Zhigang Ye, Chen Chen, Ruihuan Liu, Kai Wu, Zhaohong Bie

Enhancing restoration capabilities of distribution systems is one of the main strategies for resilient power systems to cope with extreme events.

Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines

no code implementations18 Nov 2021 Xuejing Zheng, Chao Yu, Chen Chen, Jianye Hao, Hankz Hankui Zhuo

In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which enables an agent to leverage previously learned knowledge to fasten learning of logically specified tasks.

Temporal Logic Transfer Learning

Nonnegative Tensor Completion via Integer Optimization

no code implementations8 Nov 2021 Caleb Bugg, Chen Chen, Anil Aswani

This paper develops a new algorithm for the special case of completion for nonnegative tensors.

Matrix Completion

Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersections

no code implementations24 Oct 2021 Yangang Ren, Jianhua Jiang, Dongjie Yu, Shengbo Eben Li, Jingliang Duan, Chen Chen, Keqiang Li

This paper develops the dynamic permutation state representation in the framework of integrated decision and control (IDC) to handle signalized intersections with mixed traffic flows.

Autonomous Driving Decision Making

Sim-to-Real Transfer in Multi-agent Reinforcement Networking for Federated Edge Computing

no code implementations18 Oct 2021 Pinyarash Pinyoanuntapong, Tagore Pothuneedi, Ravikumar Balakrishnan, Minwoo Lee, Chen Chen, Pu Wang

Federated Learning (FL) over wireless multi-hop edge computing networks, i. e., multi-hop FL, is a cost-effective distributed on-device deep learning paradigm.

Edge-computing Federated Learning +1

CycleFlow: Purify Information Factors by Cycle Loss

no code implementations18 Oct 2021 Haoran Sun, Chen Chen, Lantian Li, Dong Wang

SpeechFlow is a powerful factorization model based on information bottleneck (IB), and its effectiveness has been reported by several studies.

speech editing Voice Conversion

EdgeML: Towards Network-Accelerated Federated Learning over Wireless Edge

no code implementations14 Oct 2021 Pinyarash Pinyoanuntapong, Prabhu Janakaraj, Ravikumar Balakrishnan, Minwoo Lee, Chen Chen, Pu Wang

To solve such MDP, multi-agent reinforcement learning (MA-RL) algorithms along with domain-specific action space refining schemes are developed, which online learn the delay-minimum forwarding paths to minimize the model exchange latency between the edge devices (i. e., workers) and the remote server.

Edge-computing Federated Learning +1

Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition

no code implementations11 Oct 2021 Yuchen Hu, Nana Hou, Chen Chen, Eng Siong Chng

Speech enhancement (SE) aims to suppress the additive noise from a noisy speech signal to improve the speech's perceptual quality and intelligibility.

Robust Speech Recognition Speech Enhancement

Label-Occurrence-Balanced Mixup for Long-tailed Recognition

no code implementations11 Oct 2021 Shaoyu Zhang, Chen Chen, Xiujuan Zhang, Silong Peng

When applying mixup to long-tailed data, a label suppression issue arises, where the frequency of label occurrence for each class is imbalanced and most of the new examples will be completely or partially assigned with head labels.

Data Augmentation

DeepGOMIMO: Deep Learning-Aided Generalized Optical MIMO with CSI-Free Blind Detection

no code implementations8 Oct 2021 Xin Zhong, Chen Chen, Shu Fu, Zhihong Zeng, Min Liu

Generalized optical multiple-input multiple-output (GOMIMO) techniques have been recently shown to be promising for high-speed optical wireless communication (OWC) systems.

Geometric Transformers for Protein Interface Contact Prediction

1 code implementation6 Oct 2021 Alex Morehead, Chen Chen, Jianlin Cheng

Computational methods for predicting the interface contacts between proteins come highly sought after for drug discovery as they can significantly advance the accuracy of alternative approaches, such as protein-protein docking, protein function analysis tools, and other computational methods for protein bioinformatics.

Drug Discovery Translation

Uncertainty-Aware Training for Cardiac Resynchronisation Therapy Response Prediction

no code implementations22 Sep 2021 Tareen Dawood, Chen Chen, Robin Andlauer, Baldeep S. Sidhu, Bram Ruijsink, Justin Gould, Bradley Porter, Mark Elliott, Vishal Mehta, C. Aldo Rinaldi, Esther Puyol-Antón, Reza Razavi, Andrew P. King

Evaluation of predictive deep learning (DL) models beyond conventional performance metrics has become increasingly important for applications in sensitive environments like healthcare.

CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation

1 code implementation24 Aug 2021 Xidong Feng, Chen Chen, Dong Li, Mengchen Zhao, Jianye Hao, Jun Wang

Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of the model and thus allowing fast adaptation to a specific task from limited data examples.

Meta-Learning Recommendation Systems

A Novel Attribute Reconstruction Attack in Federated Learning

no code implementations16 Aug 2021 Lingjuan Lyu, Chen Chen

We perform the first systematic evaluation of attribute reconstruction attack (ARA) launched by the malicious server in the FL system, and empirically demonstrate that the shared epoch-averaged local model gradients can reveal sensitive attributes of local training data of any victim participant.

Federated Learning

Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation

1 code implementation7 Aug 2021 Chen Chen, Chen Qin, Cheng Ouyang, Shuo Wang, Huaqi Qiu, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert

The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training.

Cardiac Segmentation Data Augmentation

Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation

no code implementations8 Jul 2021 Shuo Wang, Chen Qin, Nicolo Savioli, Chen Chen, Declan O'Regan, Stuart Cook, Yike Guo, Daniel Rueckert, Wenjia Bai

In cardiac magnetic resonance (CMR) imaging, a 3D high-resolution segmentation of the heart is essential for detailed description of its anatomical structures.

Cardiac Segmentation Super-Resolution

Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation

1 code implementation2 Jul 2021 Chen Chen, Kerstin Hammernik, Cheng Ouyang, Chen Qin, Wenjia Bai, Daniel Rueckert

In this paper, we present a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples.

Data Augmentation Image Reconstruction +1

Deep Learning-Aided OFDM-Based Generalized Optical Quadrature Spatial Modulation

no code implementations24 Jun 2021 Chen Chen, Lin Zeng, Xin Zhong, Shu Fu, Min Liu, Pengfei Du

In this paper, we propose an orthogonal frequency division multiplexing (OFDM)-based generalized optical quadrature spatial modulation (GOQSM) technique for multiple-input multiple-output optical wireless communication (MIMO-OWC) systems.

Energy Aligning for Biased Models

no code implementations7 Jun 2021 Bowen Zhao, Chen Chen, Qi Ju, Shutao Xia

Training on class-imbalanced data usually results in biased models that tend to predict samples into the majority classes, which is a common and notorious problem.

class-incremental learning Incremental Learning

DIPS-Plus: The Enhanced Database of Interacting Protein Structures for Interface Prediction

1 code implementation6 Jun 2021 Alex Morehead, Chen Chen, Ada Sedova, Jianlin Cheng

In this work, we expand on a dataset recently introduced for this task, the Database of Interacting Protein Structures (DIPS), to present DIPS-Plus, an enhanced, feature-rich dataset of 42, 112 complexes for geometric deep learning of protein interfaces.

Drug Discovery Protein Interface Prediction

Fairness-Aware Unsupervised Feature Selection

no code implementations4 Jun 2021 Xiaoying Xing, Hongfu Liu, Chen Chen, Jundong Li

Feature selection is a prevalent data preprocessing paradigm for various learning tasks.

Fairness Feature Selection

Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs

no code implementations23 May 2021 Chen Chen, Xuanli He, Lingjuan Lyu, Fangzhao Wu

In this work, we bridge this gap by first presenting an effective model extraction attack, where the adversary can practically steal a BERT-based API (the target/victim model) by only querying a limited number of queries.

Inference Attack Model extraction +2

MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations

1 code implementation14 May 2021 Taojiannan Yang, Sijie Zhu, Matias Mendieta, Pu Wang, Ravikumar Balakrishnan, Minwoo Lee, Tao Han, Mubarak Shah, Chen Chen

MutualNet is a general training methodology that can be applied to various network structures (e. g., 2D networks: MobileNets, ResNet, 3D networks: SlowFast, X3D) and various tasks (e. g., image classification, object detection, segmentation, and action recognition), and is demonstrated to achieve consistent improvements on a variety of datasets.

Action Recognition Image Classification +1

Balanced Knowledge Distillation for Long-tailed Learning

1 code implementation21 Apr 2021 Shaoyu Zhang, Chen Chen, Xiyuan Hu, Silong Peng

Existing methods usually modify the classification loss to increase the learning focus on tail classes, which unexpectedly sacrifice the performance on head classes.

Knowledge Distillation

Learning Normal Dynamics in Videos with Meta Prototype Network

1 code implementation CVPR 2021 Hui Lv, Chen Chen, Zhen Cui, Chunyan Xu, Yong Li, Jian Yang

Frame reconstruction (current or future frame) based on Auto-Encoder (AE) is a popular method for video anomaly detection.

Anomaly Detection Meta-Learning

Annotating Columns with Pre-trained Language Models

no code implementations5 Apr 2021 Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çağatay Demiralp, Chen Chen, Wang-Chiew Tan

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information.

Multi-Task Learning Type prediction

Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement

1 code implementation19 Mar 2021 Kui Jiang, Zhongyuan Wang, Zheng Wang, Chen Chen, Peng Yi, Tao Lu, Chia-Wen Lin

Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps.

Low-Light Image Enhancement

Consistency-based Active Learning for Object Detection

1 code implementation18 Mar 2021 Weiping Yu, Sijie Zhu, Taojiannan Yang, Chen Chen, Mengyuan Liu

Unlike most recent works that focused on applying active learning for image classification, we propose an effective Consistency-based Active Learning method for object Detection (CALD), which fully explores the consistency between original and augmented data.

Active Learning General Classification +2

3D Human Pose Estimation with Spatial and Temporal Transformers

2 code implementations ICCV 2021 Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation.

3D Human Pose Estimation Image Classification +2

Optimal Scheduling of Integrated Demand Response-Enabled Integrated Energy Systems with Uncertain Renewable Generations: A Stackelberg Game Approach

no code implementations8 Mar 2021 Yang Li, Chunling Wang, Guoqing Li, Chen Chen

In order to balance the interests of integrated energy operator (IEO) and users, a novel Stackelberg game-based optimization framework is proposed for the optimal scheduling of integrated demand response (IDR)-enabled integrated energy systems with uncertain renewable generations, where the IEO acts as the leader who pursues the maximization of his profits by setting energy prices, while the users are the follower who adjusts energy consumption plans to minimize their energy costs.

TransBTS: Multimodal Brain Tumor Segmentation Using Transformer

1 code implementation7 Mar 2021 Wenxuan Wang, Chen Chen, Meng Ding, Jiangyun Li, Hong Yu, Sen Zha

To capture the local 3D context information, the encoder first utilizes 3D CNN to extract the volumetric spatial feature maps.

Brain Tumor Segmentation Image Classification +1

Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracy

no code implementations7 Mar 2021 Chen Chen, Kezhi Kong, Peihong Yu, Juan Luque, Tom Goldstein, Furong Huang

Randomized smoothing (RS) is an effective and scalable technique for constructing neural network classifiers that are certifiably robust to adversarial perturbations.

Enhanced 3D Human Pose Estimation from Videos by using Attention-Based Neural Network with Dilated Convolutions

1 code implementation4 Mar 2021 Ruixu Liu, Ju Shen, He Wang, Chen Chen, Sen-ching Cheung, Vijayan K. Asari

In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other forms of constraints can be incorporated into the attention framework for learning long-range dependencies for the task of pose estimation.

3D Human Pose Estimation

Addressing Action Oscillations through Learning Policy Inertia

no code implementations3 Mar 2021 Chen Chen, Hongyao Tang, Jianye Hao, Wulong Liu, Zhaopeng Meng

We propose Nested Policy Iteration as a general training algorithm for PIC-augmented policy which ensures monotonically non-decreasing updates under some mild conditions.

Atari Games Autonomous Driving +1

A Dataset and Benchmark for Malaria Life-Cycle Classification in Thin Blood Smear Images

no code implementations17 Feb 2021 Qazi Ammar Arshad, Mohsen Ali, Saeed-Ul Hassan, Chen Chen, Ayisha Imran, Ghulam Rasul, Waqas Sultani

Malaria microscopy, microscopic examination of stained blood slides to detect parasite Plasmodium, is considered to be a gold-standard for detecting life-threatening disease malaria.

General Classification

Guided Interpolation for Adversarial Training

no code implementations15 Feb 2021 Chen Chen, Jingfeng Zhang, Xilie Xu, Tianlei Hu, Gang Niu, Gang Chen, Masashi Sugiyama

To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data.

Adversarial Robustness

Bilateral attention decoder: A lightweight decoder for real-time semantic segmentation

no code implementations30 Jan 2021 Chengli Peng, Jiayi Ma, Chen Chen, Xiaojie Guo

To verify the efficiency of the proposed bilateral attention decoder, we adopt a lightweight network as the backbone and compare our proposed method with other state-of-the-art real-time semantic segmentation methods on the Cityscapes and Camvid datasets.

Real-Time Semantic Segmentation

A Transferable Anti-Forensic Attack on Forensic CNNs Using A Generative Adversarial Network

no code implementations23 Jan 2021 Xinwei Zhao, Chen Chen, Matthew C. Stamm

In this paper, we propose a new anti-forensic attack framework designed to remove forensic traces left by a variety of manipulation operations.

Towards A Category-extended Object Detector without Relabeling or Conflicts

no code implementations28 Dec 2020 Bowen Zhao, Chen Chen, Wanpeng Xiao, Xi Xiao, Qi Ju, Shutao Xia

Object detectors are typically learned based on fully-annotated training data with fixed pre-defined categories.

A3D: Adaptive 3D Networks for Video Action Recognition

no code implementations24 Nov 2020 Sijie Zhu, Taojiannan Yang, Matias Mendieta, Chen Chen

Even under the same computational constraints, the performance of our adaptive networks can be significantly boosted over the baseline counterparts by the mutual training along three dimensions.

Action Recognition

VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval

1 code implementation CVPR 2021 Sijie Zhu, Taojiannan Yang, Chen Chen

In this paper, we redefine this problem with a more realistic assumption that the query image can be arbitrary in the area of interest and the reference images are captured before the queries emerge.

Nonvolatile electric control of exciton complex in monolayer MoSe$_2$ with two dimensional ferroelectric CuInP$_2$S$_6$

no code implementations10 Nov 2020 Xiaoyu Mao, Jun Fu, Chen Chen, Yue Li, Heng Liu, Ming Gong, Hualing Zeng

With the saturated ferroelectric polarization of CIPS, electron-doped or hole-doped MoSe$_2$ is realized in a single device with a large carrier density tunability up to $5\times 10^{12}$cm$^{-2}$.

Materials Science

Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection

1 code implementation7 Nov 2020 Weiping Yu, Taojiannan Yang, Chen Chen

To this end, we rethink long-tailed object detection in UAV images and propose the Dual Sampler and Head detection Network (DSHNet), which is the first work that aims to resolve long-tail distribution in UAV images.

Head Detection Image Cropping

On the Transformer Growth for Progressive BERT Training

no code implementations NAACL 2021 Xiaotao Gu, Liyuan Liu, Hongkun Yu, Jing Li, Chen Chen, Jiawei Han

Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational complexity.

Language Modelling

What About Inputing Policy in Value Function: Policy Representation and Policy-extended Value Function Approximator

no code implementations NeurIPS 2021 Hongyao Tang, Zhaopeng Meng, Jianye Hao, Chen Chen, Daniel Graves, Dong Li, Changmin Yu, Hangyu Mao, Wulong Liu, Yaodong Yang, Wenyuan Tao, Li Wang

We study Policy-extended Value Function Approximator (PeVFA) in Reinforcement Learning (RL), which extends conventional value function approximator (VFA) to take as input not only the state (and action) but also an explicit policy representation.

Continuous Control Contrastive Learning +2

Progressive Bilateral-Context Driven Model for Post-Processing Person Re-Identification

1 code implementation7 Sep 2020 Min Cao, Chen Chen, Hao Dou, Xiyuan Hu, Silong Peng, Arjan Kuijper

Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric.

Large-Scale Person Re-Identification

Stochastic Adaptive Line Search for Differentially Private Optimization

no code implementations18 Aug 2020 Chen Chen, Jaewoo Lee

In this paper, we introduce a stochastic variant of classic backtracking line search algorithm that satisfies R\'enyi differential privacy.

Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification

1 code implementation2 Aug 2020 Yu Shen, Sijie Zhu, Chen Chen, Qian Du, Liang Xiao, Jianyu Chen, Delu Pan

Therefore, to incorporate the long-range contextual information, a deep fully convolutional network (FCN) with an efficient non-local module, named ENL-FCN, is proposed for HSI classification.

General Classification Hyperspectral Image Classification

Lightweight image super-resolution with enhanced CNN

1 code implementation8 Jul 2020 Chunwei Tian, Ruibin Zhuge, Zhihao Wu, Yong Xu, WangMeng Zuo, Chen Chen, Chia-Wen Lin

Finally, the IRB uses coarse high-frequency features from the RB to learn more accurate SR features and construct a SR image.

Image Super-Resolution

Go Wide, Then Narrow: Efficient Training of Deep Thin Networks

no code implementations ICML 2020 Denny Zhou, Mao Ye, Chen Chen, Tianjian Meng, Mingxing Tan, Xiaodan Song, Quoc Le, Qiang Liu, Dale Schuurmans

This is achieved by layerwise imitation, that is, forcing the thin network to mimic the intermediate outputs of the wide network from layer to layer.

Model Compression

Deep Generative Model-based Quality Control for Cardiac MRI Segmentation

no code implementations23 Jun 2020 Shuo Wang, Giacomo Tarroni, Chen Qin, Yuanhan Mo, Chengliang Dai, Chen Chen, Ben Glocker, Yike Guo, Daniel Rueckert, Wenjia Bai

Our approach provides a real-time and model-agnostic quality control for cardiac MRI segmentation, which has the potential to be integrated into clinical image analysis workflows.

MRI segmentation

Realistic Adversarial Data Augmentation for MR Image Segmentation

1 code implementation23 Jun 2020 Chen Chen, Chen Qin, Huaqi Qiu, Cheng Ouyang, Shuo Wang, Liang Chen, Giacomo Tarroni, Wenjia Bai, Daniel Rueckert

In this work, we propose an adversarial data augmentation method for training neural networks for medical image segmentation.

Data Augmentation Medical Image Segmentation

Robust Federated Recommendation System

no code implementations15 Jun 2020 Chen Chen, Jingfeng Zhang, Anthony K. H. Tung, Mohan Kankanhalli, Gang Chen

We argue that the key to Byzantine detection is monitoring of gradients of the model parameters of clients.

Recommendation Systems

GradAug: A New Regularization Method for Deep Neural Networks

1 code implementation NeurIPS 2020 Taojiannan Yang, Sijie Zhu, Chen Chen

The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the original network, in the training process.

Instance Segmentation Object Detection +1

Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI

1 code implementation8 Jun 2020 Chen Qin, Shuo Wang, Chen Chen, Huaqi Qiu, Wenjia Bai, Daniel Rueckert

The learnt VAE regulariser then can be coupled with any deep learning based registration network to regularise the solution space to be biomechanically plausible.

Image Registration

Twitter discussions and emotions about COVID-19 pandemic: a machine learning approach

no code implementations26 May 2020 Jia Xue, Junxiang Chen, Ran Hu, Chen Chen, Chengda Zheng, Xiaoqian Liu, Tingshao Zhu

Across all identified topics, the dominant sentiments for the spread of coronavirus are anticipation that measures that can be taken, followed by a mixed feeling of trust, anger, and fear for different topics.

Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation

no code implementations23 May 2020 Sijie Zhu, Taojiannan Yang, Chen Chen

Street-to-aerial image geo-localization, which matches a query street-view image to the GPS-tagged aerial images in a reference set, has attracted increasing attention recently.

Metric Learning

NOMA for Energy-Efficient LiFi-Enabled Bidirectional IoT Communication

no code implementations20 May 2020 Chen Chen, Shu Fu, Xin Jian, Min Liu, Xiong Deng, Zhiguo Ding

In order to improve the energy efficiency (EE) of the bidirectional LiFi-IoT system, non-orthogonal multiple access (NOMA) with a quality-of-service (QoS)-guaranteed optimal power allocation (OPA) strategy is applied to maximize the EE of the system.

Recognizing Exercises and Counting Repetitions in Real Time

no code implementations7 May 2020 Talal Alatiah, Chen Chen

Artificial intelligence technology has made its way absolutely necessary in a variety of industries including the fitness industry.

Pose Estimation

PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution

no code implementations1 May 2020 Hao Dou, Chen Chen, Xiyuan Hu, Zuxing Xuan, Zhisen Hu, Silong Peng

Generative Adversarial Networks (GAN) have been employed for face super resolution but they bring distorted facial details easily and still have weakness on recovering realistic texture.


CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks

no code implementations30 Apr 2020 Li'an Zhuo, Baochang Zhang, Hanlin Chen, Linlin Yang, Chen Chen, Yanjun Zhu, David Doermann

To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent).

Neural Architecture Search

Action recognition in real-world videos

no code implementations22 Apr 2020 Waqas Sultani, Qazi Ammar Arshad, Chen Chen

Temporal localization (i. e. indicating the start and end frames of the action in a video) is referred to as frame-level detection.

Action Recognition Temporal Localization

Density Map Guided Object Detection in Aerial Images

1 code implementation12 Apr 2020 Changlin Li, Taojiannan Yang, Sijie Zhu, Chen Chen, Shanyue Guan

Specifically, we propose a Density-Map guided object detection Network (DMNet), which is inspired from the observation that the object density map of an image presents how objects distribute in terms of the pixel intensity of the map.

Image Cropping Object Detection In Aerial Images +1

Enhancing Review Comprehension with Domain-Specific Commonsense

no code implementations6 Apr 2020 Aaron Traylor, Chen Chen, Behzad Golshan, Xiaolan Wang, Yuliang Li, Yoshihiko Suhara, Jinfeng Li, Cagatay Demiralp, Wang-Chiew Tan

In this paper, we introduce xSense, an effective system for review comprehension using domain-specific commonsense knowledge bases (xSense KBs).

Aspect Extraction Knowledge Distillation +2

Video Anomaly Detection for Smart Surveillance

no code implementations1 Apr 2020 Sijie Zhu, Chen Chen, Waqas Sultani

Temporal localization (i. e. indicating the start and end frames of the anomaly event in a video) is referred to as frame-level detection.

Anomaly Detection Temporal Localization

Multi-Scale Progressive Fusion Network for Single Image Deraining

1 code implementation CVPR 2020 Kui Jiang, Zhongyuan Wang, Peng Yi, Chen Chen, Baojin Huang, Yimin Luo, Jiayi Ma, Junjun Jiang

In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal.

Single Image Deraining

Robust Synthesis of Wind Turbine Generators to Support Microgrid Frequency Considering Linearization-Induced Uncertainty

no code implementations5 Mar 2020 Yichen Zhang, Chen Chen, Tianqi Hong, Bai Cui, Bo Chen, Feng Qiu

The capability to switch between grid-connected and islanded modes has promoted adoption of microgrid technology for powering remote locations.

Sampo: Unsupervised Knowledge Base Construction for Opinions and Implications

1 code implementation AKBC 2020 Nikita Bhutani, Aaron Traylor, Chen Chen, Xiaolan Wang, Behzad Golshan, Wang-Chiew Tan

Since it can be expensive to obtain training data to learn to extract implications for each new domain of reviews, we propose an unsupervised KBC system, Sampo, Specifically, Sampo is tailored to build KBs for domains where many reviews on the same domain are available.

An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models

1 code implementation6 Feb 2020 Yao Deng, Xi Zheng, Tianyi Zhang, Chen Chen, Guannan Lou, Miryung Kim

We derive several implications for system and middleware builders: (1) when adding a defense component against adversarial attacks, it is important to deploy multiple defense methods in tandem to achieve a good coverage of various attacks, (2) a blackbox attack is much less effective compared with a white-box attack, implying that it is important to keep model details (e. g., model architecture, hyperparameters) confidential via model obfuscation, and (3) driving models with a complex architecture are preferred if computing resources permit as they are more resilient to adversarial attacks than simple models.

Autonomous Driving

Approximating Trajectory Constraints with Machine Learning -- Microgrid Islanding with Frequency Constraints

no code implementations16 Jan 2020 Yichen Zhang, Chen Chen, Guodong Liu, Tianqi Hong, Feng Qiu

In this paper, we introduce a deep learning aided constraint encoding method to tackle the frequency-constraint microgrid scheduling problem.

HMTNet:3D Hand Pose Estimation from Single Depth Image Based on Hand Morphological Topology

no code implementations12 Nov 2019 Weiguo Zhou, Xin Jiang, Chen Chen, Sijia Mei, Yun-hui Liu

In this paper, we propose a method that takes advantage of human hand morphological topology (HMT) structure to improve the pose estimation performance.

Robotics Human-Computer Interaction

Multilingual Dialogue Generation with Shared-Private Memory

no code implementations6 Oct 2019 Chen Chen, Lisong Qiu, Zhenxin Fu, Dongyan Zhao, Junfei Liu, Rui Yan

Existing dialog systems are all monolingual, where features shared among different languages are rarely explored.

Cross-Lingual Transfer Dialogue Generation

Seeing Motion in the Dark

1 code implementation ICCV 2019 Chen Chen, Qifeng Chen, Minh N. Do, Vladlen Koltun

By carefully designing a learning-based pipeline and introducing a new loss function to encourage temporal stability, we train a siamese network on static raw videos, for which ground truth is available, such that the network generalizes to videos of dynamic scenes at test time.

MGHRL: Meta Goal-generation for Hierarchical Reinforcement Learning

no code implementations30 Sep 2019 Haotian Fu, Hongyao Tang, Jianye Hao, Wulong Liu, Chen Chen

Most meta reinforcement learning (meta-RL) methods learn to adapt to new tasks by directly optimizing the parameters of policies over primitive action space.

Hierarchical Reinforcement Learning Meta-Learning +1

Visual Explanation for Deep Metric Learning

1 code implementation27 Sep 2019 Sijie Zhu, Taojiannan Yang, Chen Chen

This work explores the visual explanation for deep metric learning and its applications.

Metric Learning

MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution

2 code implementations ECCV 2020 Taojiannan Yang, Sijie Zhu, Chen Chen, Shen Yan, Mi Zhang, Andrew Willis

We propose the width-resolution mutual learning method (MutualNet) to train a network that is executable at dynamic resource constraints to achieve adaptive accuracy-efficiency trade-offs at runtime.

Instance Segmentation Object Detection +2

Renyi Differentially Private ADMM for Non-Smooth Regularized Optimization

no code implementations18 Sep 2019 Chen Chen, Jaewoo Lee

In this paper we consider the problem of minimizing composite objective functions consisting of a convex differentiable loss function plus a non-smooth regularization term, such as $L_1$ norm or nuclear norm, under R\'enyi differential privacy (RDP).

Feature Selection

Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation

no code implementations20 Aug 2019 Chen Chen, Cheng Ouyang, Giacomo Tarroni, Jo Schlemper, Huaqi Qiu, Wenjia Bai, Daniel Rueckert

In this work, we present a fully automatic method to segment cardiac structures from late-gadolinium enhanced (LGE) images without using labelled LGE data for training, but instead by transferring the anatomical knowledge and features learned on annotated balanced steady-state free precession (bSSFP) images, which are easier to acquire.

Semantic Segmentation Style Transfer +1

Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction

no code implementations5 Jul 2019 Wenjia Bai, Chen Chen, Giacomo Tarroni, Jinming Duan, Florian Guitton, Steffen E. Petersen, Yike Guo, Paul M. Matthews, Daniel Rueckert

In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks.

Self-Supervised Learning Semantic Segmentation +1

Improving the generalizability of convolutional neural network-based segmentation on CMR images

1 code implementation2 Jul 2019 Chen Chen, Wenjia Bai, Rhodri H. Davies, Anish N. Bhuva, Charlotte Manisty, James C. Moon, Nay Aung, Aaron M. Lee, Mihir M. Sanghvi, Kenneth Fung, Jose Miguel Paiva, Steffen E. Petersen, Elena Lukaschuk, Stefan K. Piechnik, Stefan Neubauer, Daniel Rueckert

We demonstrate that a neural network trained on a single-site single-scanner dataset from the UK Biobank can be successfully applied to segmenting cardiac MR images across different sites and different scanners without substantial loss of accuracy.

Semantic Segmentation

GeoCapsNet: Aerial to Ground view Image Geo-localization using Capsule Network

no code implementations12 Apr 2019 Bin Sun, Chen Chen, Yingying Zhu, Jianmin Jiang

The task of cross-view image geo-localization aims to determine the geo-location (GPS coordinates) of a query ground-view image by matching it with the GPS-tagged aerial (satellite) images in a reference dataset.

Image Retrieval

Rain Removal By Image Quasi-Sparsity Priors

no code implementations20 Dec 2018 Yinglong Wang, Shuaicheng Liu, Chen Chen, Dehua Xie, Bing Zeng

We present a novel rain removal method in this paper, which consists of two steps, i. e., detection of rain streaks and reconstruction of the rain-removed image.

Rain Removal

MGANet: A Robust Model for Quality Enhancement of Compressed Video

2 code implementations22 Nov 2018 Xiandong Meng, Xuan Deng, Shuyuan Zhu, Shuaicheng Liu, Chuan Wang, Chen Chen, Bing Zeng

In video compression, most of the existing deep learning approaches concentrate on the visual quality of a single frame, while ignoring the useful priors as well as the temporal information of adjacent frames.

Video Compression

Multi-Task Learning for Left Atrial Segmentation on GE-MRI

1 code implementation31 Oct 2018 Chen Chen, Wenjia Bai, Daniel Rueckert

Segmentation of the left atrium (LA) is crucial for assessing its anatomy in both pre-operative atrial fibrillation (AF) ablation planning and post-operative follow-up studies.

General Classification Multi-Task Learning

Hyperspectral Image Classification in the Presence of Noisy Labels

1 code implementation12 Sep 2018 Junjun Jiang, Jiayi Ma, Zheng Wang, Chen Chen, Xian-Ming Liu

The key idea of RLPA is to exploit knowledge (e. g., the superpixel based spectral-spatial constraints) from the observed hyperspectral images and apply it to the process of label propagation.

General Classification Hyperspectral Image Classification

SuperPCA: A Superpixelwise PCA Approach for Unsupervised Feature Extraction of Hyperspectral Imagery

1 code implementation26 Jun 2018 Junjun Jiang, Jiayi Ma, Chen Chen, Zhongyuan Wang, Zhihua Cai, Lizhe Wang

(1) Unlike the traditional PCA method based on a whole image, SuperPCA takes into account the diversity in different homogeneous regions, that is, different regions should have different projections.

Dimensionality Reduction General Classification

Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments

no code implementations7 Jun 2018 Chen Chen, Qizhen Weng, Wei Wang, Baochun Li, Bo Li

Efficient model training requires eliminating such stragglers, yet for modern ML workloads, existing load balancing strategies are inefficient and even infeasible.

Key Person Aided Re-identification in Partially Ordered Pedestrian Set

no code implementations25 May 2018 Chen Chen, Min Cao, Xiyuan Hu, Silong Peng

Ideally person re-identification seeks for perfect feature representation and metric model that re-identify all various pedestrians well in non-overlapping views at different locations with different camera configurations, which is very challenging.

Person Re-Identification

Improving Image Captioning with Conditional Generative Adversarial Nets

1 code implementation18 May 2018 Chen Chen, Shuai Mu, Wanpeng Xiao, Zexiong Ye, Liesi Wu, Qi Ju

In this paper, we propose a novel conditional-generative-adversarial-nets-based image captioning framework as an extension of traditional reinforcement-learning (RL)-based encoder-decoder architecture.

Image Captioning

Memory Attention Networks for Skeleton-based Action Recognition

1 code implementation23 Apr 2018 Chunyu Xie, Ce Li, Baochang Zhang, Chen Chen, Jungong Han, Changqing Zou, Jianzhuang Liu

Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence.

Action Recognition Skeleton Based Action Recognition

Real-world Anomaly Detection in Surveillance Videos

6 code implementations CVPR 2018 Waqas Sultani, Chen Chen, Mubarak Shah

To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i. e. the training labels (anomalous or normal) are at video-level instead of clip-level.

Activity Recognition Anomaly Detection In Surveillance Videos +2

Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions

no code implementations4 Dec 2017 Mengyuan Liu, Hong Liu, Chen Chen

Then, motion and shape cues are jointly used to generate robust and distinctive spatial-temporal interest points (STIPs): motion-based STIPs and shape-based STIPs.

3D Action Recognition

An End-to-end 3D Convolutional Neural Network for Action Detection and Segmentation in Videos

no code implementations30 Nov 2017 Rui Hou, Chen Chen, Mubarak Shah

A video is first divided into equal length clips and next for each clip a set of tube proposals are generated based on 3D CNN features.

Action Detection Action Segmentation +3

Latent Constrained Correlation Filter

no code implementations11 Nov 2017 Baochang Zhang, Shangzhen Luan, Chen Chen, Jungong Han, Wei Wang, Alessandro Perina, Ling Shao

In this paper, we introduce an intermediate step -- solution sampling -- after the data sampling step to form a subspace, in which an optimal solution can be estimated.

Object Recognition Object Tracking

Multi-modal Aggregation for Video Classification

no code implementations27 Oct 2017 Chen Chen, Xiaowei Zhao, Yang Liu

In this paper, we present a solution to Large-Scale Video Classification Challenge (LSVC2017) [1] that ranked the 1st place.

General Classification Video Classification

Manifold Constrained Low-Rank Decomposition

no code implementations6 Aug 2017 Chen Chen, Baochang Zhang, Alessio Del Bue, Vittorio Murino

Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling.

Fast Modeling Methods for Complex System with Separable Features

no code implementations5 Aug 2017 Chen Chen, Changtong Luo, Zonglin Jiang

In this paper, we analyze different types of separability of some real-world engineering equations and establish a mathematical model of generalized separable system (GS system).

Binary Coding for Partial Action Analysis With Limited Observation Ratios

no code implementations CVPR 2017 Jie Qin, Li Liu, Ling Shao, Bingbing Ni, Chen Chen, Fumin Shen, Yunhong Wang

Extensive experiments on four realistic action datasets in terms of three tasks (i. e., partial action retrieval, recognition and prediction) clearly show the superiority of PRBC over the state-of-the-art methods, along with significantly reduced memory load and computational costs during the online test.

Action Analysis Action Recognition +1

A divide and conquer method for symbolic regression

no code implementations23 May 2017 Changtong Luo, Chen Chen, Zonglin Jiang

This feature motivated us to develop a new method, divide and conquer (D&C), for symbolic regression, in which the target function is divided into a number of sub-functions and the sub-functions are then determined by any of a GP algorithm.

Block building programming for symbolic regression

no code implementations22 May 2017 Chen Chen, Changtong Luo, Zonglin Jiang

Symbolic regression that aims to detect underlying data-driven models has become increasingly important for industrial data analysis.

Gabor Convolutional Networks

no code implementations3 May 2017 Shangzhen Luan, Baochang Zhang, Chen Chen, Xian-Bin Cao, Jungong Han, Jianzhuang Liu

Steerable properties dominate the design of traditional filters, e. g., Gabor filters, and endow features the capability of dealing with spatial transformations.

Elite Bases Regression: A Real-time Algorithm for Symbolic Regression

no code implementations24 Apr 2017 Chen Chen, Changtong Luo, Zonglin Jiang

In this paper, a new non-evolutionary real-time algorithm for symbolic regression, Elite Bases Regression (EBR), is proposed.

Tube Convolutional Neural Network (T-CNN) for Action Detection in Videos

1 code implementation ICCV 2017 Rui Hou, Chen Chen, Mubarak Shah

A video is first divided into equal length clips and for each clip a set of tube proposals are generated next based on 3D Convolutional Network (ConvNet) features.

Action Detection Image Classification +1

Cross-View Image Matching for Geo-localization in Urban Environments

1 code implementation CVPR 2017 Yicong Tian, Chen Chen, Mubarak Shah

Next, for each building in the query image, we retrieve the $k$ nearest neighbors from the reference buildings using a Siamese network trained on both positive matching image pairs and negative pairs.

Cross-View Image-to-Image Translation Image Classification +1

Semantic Image Inpainting with Deep Generative Models

6 code implementations CVPR 2017 Raymond A. Yeh, Chen Chen, Teck Yian Lim, Alexander G. Schwing, Mark Hasegawa-Johnson, Minh N. Do

In this paper, we propose a novel method for semantic image inpainting, which generates the missing content by conditioning on the available data.

Image Inpainting

A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method

1 code implementation3 Jul 2016 Yuzhuo Ren, Chen Chen, Shang-Wen Li, C. -C. Jay Kuo

The task of estimating the spatial layout of cluttered indoor scenes from a single RGB image is addressed in this work.

Latent Constrained Correlation Filters for Object Localization

no code implementations7 Jun 2016 Shangzhen Luan, Baochang Zhang, Jungong Han, Chen Chen, Ling Shao, Alessandro Perina, Linlin Shen

There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling.

Object Localization

GAL: A Global-Attributes Assisted Labeling System for Outdoor Scenes

no code implementations3 Apr 2016 Yuzhuo Ren, Chen Chen, Shang-Wen Li, C. -C. Jay Kuo

The proposed Global-attributes Assisted Labeling (GAL) system exploits both local features and global attributes.

Measuring and Predicting Tag Importance for Image Retrieval

no code implementations28 Feb 2016 Shang-Wen Li, Sanjay Purushotham, Chen Chen, Yuzhuo Ren, C. -C. Jay Kuo

Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today's Multimodal Image Retrieval (MIR) systems.

Image Retrieval TAG

Fast Iteratively Reweighted Least Squares Algorithms for Analysis-Based Sparsity Reconstruction

no code implementations18 Nov 2014 Chen Chen, Junzhou Huang, Lei He, Hongsheng Li

The convergence rate of the proposed algorithm is almost the same as that of the traditional IRLS algorithms, that is, exponentially fast.

Compressive Sensing

SIRF: Simultaneous Image Registration and Fusion in A Unified Framework

no code implementations18 Nov 2014 Chen Chen, Yeqing Li, Wei Liu, Junzhou Huang

In this paper, we propose a novel method for image fusion with a high-resolution panchromatic image and a low-resolution multispectral image at the same geographical location.

Image Registration

Image Fusion with Local Spectral Consistency and Dynamic Gradient Sparsity

no code implementations CVPR 2014 Chen Chen, Yeqing Li, Wei Liu, Junzhou Huang

In this paper, we propose a novel method for image fusion from a high resolution panchromatic image and a low resolution multispectral image at the same geographical location.

Compressive Sensing MRI with Wavelet Tree Sparsity

no code implementations NeurIPS 2012 Chen Chen, Junzhou Huang

On the other side, some algorithms have been proposed for tree sparsity regularization, but few of them has validated the benefit of tree structure in CS-MRI.

Compressive Sensing

Forest Sparsity for Multi-channel Compressive Sensing

no code implementations20 Nov 2012 Chen Chen, Yeqing Li, Junzhou Huang

In this paper, we investigate a new compressive sensing model for multi-channel sparse data where each channel can be represented as a hierarchical tree and different channels are highly correlated.

Compressive Sensing

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