no code implementations • 27 Jun 2022 • Jun Li, Yushan Zheng, Kun Wu, Jun Shi, Fengying Xie, Zhiguo Jiang
In this paper, we proposed a novel contrastive representation learning framework named Lesion-Aware Contrastive Learning (LACL) for histopathology whole slide image analysis.
1 code implementation • 27 Jun 2022 • Yushan Zheng, Jun Li, Jun Shi, Fengying Xie, Zhiguo Jiang
Transformer has been widely used in histopathology whole slide image (WSI) classification for the purpose of tumor grading, prognosis analysis, etc.
no code implementations • 19 Jun 2022 • Jun Li, Shibo Li, Ying Hu, Huiren Tao
Moreover, SGF successfully improves the accuracy and length of medical report generation by incorporating a similarity comparison mechanism that imitates the process of human self-improvement through compar-ative practice.
no code implementations • 14 Jun 2022 • Jun Li, Yifan Lin, Nan Xie
This technology could shift the measured signal frequency band from near 50 Hz moved to several kilometer Hz, so as to make the output signal avoid the interference from low-frequency temperature drift, stress birefringence and vibration, leading to higher stability and reliability.
1 code implementation • 6 Jun 2022 • Hulin Li, Jun Li, Hanbing Wei, Zheng Liu, Zhenfei Zhan, Qiliang Ren
We introduce a new method, GSConv, to lighten the model but maintain the accuracy.
no code implementations • 2 Jun 2022 • Jun Li, Junyu Chen, Yucheng Tang, Ce Wang, Bennett A. Landman, S. Kevin Zhou
Transformer, the latest technological advance of deep learning, has gained prevalence in natural language processing or computer vision.
no code implementations • 30 May 2022 • Jun Li, Shangwei Guo, Shaokun Han
Point cloud completion task aims to predict the missing part of incomplete point clouds and generate complete point clouds with details.
no code implementations • 17 May 2022 • Xin Cheng, Tingting Liu, Feng Shu, Chuan Ma, Jun Li, Jiangzhou Wang
Recently, the development of mobile edge computing has enabled exhilarating edge artificial intelligence (AI) with fast response and low communication cost.
no code implementations • ICLR 2022 • Jianwen Xie, Yaxuan Zhu, Jun Li, Ping Li
Under the short-run non-mixing MCMC scenario, the estimation of the energy-based model is shown to follow the perturbation of maximum likelihood, and the short-run Langevin flow and the normalizing flow form a two-flow generator that we call CoopFlow.
no code implementations • 10 May 2022 • Bing Zhao, Jun Li, Hong Zhu
To bridge the performance gap, we propose a novel object-level self-supervised learning method, called Contrastive learning with Downstream background invariance (CoDo).
no code implementations • 18 Apr 2022 • Jun Yue, Leyuan Fang, Pedram Ghamisi, Weiying Xie, Jun Li, Jocelyn Chanussot, Antonio J Plaza
Therefore, remote sensing image understanding often faces the problems of incomplete, inexact, and inaccurate supervised information, which will affect the breadth and depth of remote sensing applications.
no code implementations • 9 Apr 2022 • Heng-Chao Li, Wen-Shuai Hu, Wei Li, Jun Li, Qian Du, Antonio Plaza
The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing.
1 code implementation • 7 Apr 2022 • Ting Zhang, Jun Li, Yi Zhao, Nan Chen, Han Zhou, Hongtao Xu, Zihao Guan, Changcai Yang, Lanyan Xue, Riqing Chen, Lifang Wei
The proposed network structure retains three layers the essential structure of U-Net, in which the atrous convolution combining the multi-kernel pooling blocks are designed to obtain more contextual information.
no code implementations • 3 Apr 2022 • Tae-Kyoung Kim, Yo-Seb Jeon, Jun Li, Nima Tavangaran, H. Vincent Poor
Data-aided channel estimation is a promising solution to improve channel estimation accuracy by exploiting data symbols as pilot signals for updating an initial channel estimate.
no code implementations • 30 Mar 2022 • Asim Ihsan, Wen Chen, Muhammad Asif, Wali Ullah Khan, Jun Li
This manuscript presents an energy-efficient alternating optimization framework based on intelligent reflective surfaces (IRS) aided non-orthogonal multiple access beamforming (NOMA-BF) system for 6G wireless communications.
no code implementations • 29 Mar 2022 • Xin Cheng, Chuan Ma, Jun Li, Haiwei Song, Feng Shu, Jiangzhou Wang
Fingerprint-based localization plays an important role in indoor location-based services, where the position information is usually collected in distributed clients and gathered in a centralized server.
1 code implementation • CVPR 2022 • Jun Li, Zichang Tan, Jun Wan, Zhen Lei, Guodong Guo
NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively.
Ranked #1 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
no code implementations • 26 Mar 2022 • Jie Zhang, Jun Li, Yijin Zhang, Qingqing Wu, Xiongwei Wu, Feng Shu, Shi Jin, Wen Chen
Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks.
1 code implementation • CVPR 2022 • Jinchao Yang, Fei Guo, Shuo Chen, Jun Li, Jian Yang
Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product.
no code implementations • 18 Mar 2022 • Zhiqiang Yan, Xiang Li, Kun Wang, Zhenyu Zhang, Jun Li, Jian Yang
Specifically, during pre-training, we simultaneously cover up patches of the panoramic RGB image and sparse depth by shared random mask, then reconstruct the sparse depth in the masked regions.
no code implementations • 4 Mar 2022 • Pengbo Liu, Yang Deng, Ce Wang, Yuan Hui, Qian Li, Jun Li, Shiwei Luo, Mengke Sun, Quan Quan, Shuxin Yang, You Hao, Honghu Xiao, Chunpeng Zhao, Xinbao Wu, S. Kevin Zhou
Firstly, while it is ideal to learn such a model from a large-scale, fully-annotated dataset, it is practically hard to curate such a dataset.
no code implementations • 4 Mar 2022 • Jun Li, Quan Quan, S. Kevin Zhou
It is essential for medical image analysis, which is often notorious for its lack of annotations.
no code implementations • 21 Feb 2022 • Zhijun Zeng, Zhen Hou, Ting Li, Lei Deng, Jianguo Hou, Xinran Huang, Jun Li, Meirou Sun, Yunhan Wang, Qiyu Wu, Wenhao Zheng, Hua Jiang, Qi Wang
We develop a deep learning approach to predicting a set of ventilator parameters for a mechanically ventilated septic patient using a long and short term memory (LSTM) recurrent neural network (RNN) model.
no code implementations • 9 Feb 2022 • Kang Wei, Jun Li, Chuan Ma, Ming Ding, Sha Wei, Fan Wu, Guihai Chen, Thilina Ranbaduge
As a special architecture in FL, vertical FL (VFL) is capable of constructing a hyper ML model by embracing sub-models from different clients.
no code implementations • 7 Feb 2022 • Pedro Soto, Haibin Guan, Jun Li
We introduce a new metric for analysis called the typical recovery threshold, which focuses on the most likely event and provide a novel construction of distributed coded tensor operations which are optimal with this measure.
no code implementations • 31 Jan 2022 • Pedro Soto, Ilia Ilmer, Haibin Guan, Jun Li
Coded distributed computation has become common practice for performing gradient descent on large datasets to mitigate stragglers and other faults.
no code implementations • 14 Dec 2021 • Yongkang Zhang, Jun Li, Guoming Wu, Han Zhang, Zhiping Shi, Zhaoxun Liu, Zizhang Wu, Na Jiang
The temporal sequence self-supervision module we employ unprecedentedly adopts the streamlined strategy of "random batch random channel" to reverse the sequence of video frames, allowing robust extractions of motion information representation from inversed temporal dimensions and improving the generalization capability of the model.
no code implementations • CVPR 2022 • Quan Quan, Qingsong Yao, Jun Li, S. Kevin Zhou
We herein propose a novel Sample Choosing Policy (SCP) to select "the most worthy" images for annotation, in the context of few-shot medical landmark detection.
no code implementations • 30 Nov 2021 • Shangwei Guo, Jun Li, Zhengchao Lai, Xiantong Meng, Shaokun Han
Meanwhile, the transformer-branch performs offset-attention process on the whole point cloud to extract the global feature.
no code implementations • 17 Nov 2021 • Xi Cheng, Jun Li, Qiang Dai, ZhenYong Fu, Jian Yang
In our SF-SIM, we propose a noise estimator which can effectively suppress the noise in the image and enable our method to work under the low light and short exposure environment, without the need for stacking multiple frames for non-local denoising.
no code implementations • 27 Oct 2021 • Runmin Cong, Yumo Zhang, Leyuan Fang, Jun Li, Yao Zhao, Sam Kwong
Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs.
no code implementations • 29 Sep 2021 • Jun Li, Ping Li
In this paper, we propose a $f$-divergence Thermodynamic Variational Objective ($f$-TVO).
no code implementations • ICLR 2022 • Tan Yu, Jun Li, Yunfeng Cai, Ping Li
A convolution layer with an orthogonal Jacobian matrix is 1-Lipschitz in the 2-norm, making the output robust to the perturbation in input.
no code implementations • 29 Sep 2021 • Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, H. Vincent Poor
The convergence of mobile edge computing (MEC) and blockchain is transforming the current computing services in mobile networks, by offering task offloading solutions with security enhancement empowered by blockchain mining.
1 code implementation • ICCV 2021 • Haobo Jiang, Yaqi Shen, Jin Xie, Jun Li, Jianjun Qian, Jian Yang
Based on the reward function, for each state, we then construct a fused score function to evaluate the sampled transformations, where we weight the current and future rewards of the transformations.
2 code implementations • CVPR 2021 • Changsu Cao, Jiaqi Hu, Wengang Zhang, Xusheng Xu, Dechin Chen, Fan Yu, Jun Li, Hanshi Hu, Dingshun Lv, Man-Hong Yung
We also propose a lossless compression algorithm based on iVPF.
no code implementations • 23 Aug 2021 • Yifan Liu, Bin Duo, Qingqing Wu, Xiaojun Yuan, Jun Li, Yonghui Li
This paper investigates an aerial reconfigurable intelligent surface (RIS)-aided communication system under the probabilistic line-of-sight (LoS) channel, where an unmanned aerial vehicle (UAV) equipped with an RIS is deployed to assist two ground nodes in their information exchange.
no code implementations • 11 Aug 2021 • Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, Dusit Niyato, Octavia Dobre, H. Vincent Poor
The sixth generation (6G) wireless communication networks are envisioned to revolutionize customer services and applications via the Internet of Things (IoT) towards a future of fully intelligent and autonomous systems.
1 code implementation • ICCV 2021 • Kun Wang, Zhenyu Zhang, Zhiqiang Yan, Xiang Li, Baobei Xu, Jun Li, Jian Yang
Monocular depth estimation aims at predicting depth from a single image or video.
no code implementations • 8 Aug 2021 • Jun Li, Shimei Chen, Shangyuan Wang, Miao Lei, Xiaofang Dai, Chuangxue Liang, Kunyuan Xu, Shuxin Lin, Yuhui Li, Yuer Fan, Ting Zhong
We presented an optical system to perform imaging interested objects in complex scenes, like the creature easy see the interested prey in the hunt for complex environments.
no code implementations • 29 Jul 2021 • Zhiqiang Yan, Kun Wang, Xiang Li, Zhenyu Zhang, Baobei Xu, Jun Li, Jian Yang
Depth completion deals with the problem of recovering dense depth maps from sparse ones, where color images are often used to facilitate this task.
Ranked #2 on
Depth Completion
on KITTI Depth Completion
no code implementations • 23 Jul 2021 • Zhendong Li, Wen Chen, Huanqing Cao, Hongying Tang, Kunlun Wang, Jun Li
Aiming at the limited battery capacity of widely deployed low-power smart devices in the Internet-of-things (IoT), this paper proposes a novel intelligent reflecting surface (IRS) empowered unmanned aerial vehicle (UAV) simultaneous wireless information and power transfer (SWIPT) network framework, in which IRS is used to reconstruct the wireless channel to enhance the wireless energy transmission efficiency and coverage area of the UAV SWIPT networks.
no code implementations • 20 Jun 2021 • Kang Wei, Jun Li, Chuan Ma, Ming Ding, Cailian Chen, Shi Jin, Zhu Han, H. Vincent Poor
Then, we convert the MAMAB to a max-min bipartite matching problem at each communication round, by estimating rewards with the upper confidence bound (UCB) approach.
no code implementations • 5 Jun 2021 • Huanan Wang, Xinyu Zhang, Jun Li, Zhiwei Li, Lei Yang, Shuyue Pan, Yongqiang Deng
Through an IPS (Intersection Perception System) installed at the diagonal of the intersection, this paper proposes a high-quality multimodal dataset for the intersection perception task.
1 code implementation • 31 May 2021 • Yang Deng, Ce Wang, Yuan Hui, Qian Li, Jun Li, Shiwei Luo, Mengke Sun, Quan Quan, Shuxin Yang, You Hao, Pengbo Liu, Honghu Xiao, Chunpeng Zhao, Xinbao Wu, S. Kevin Zhou
Spine-related diseases have high morbidity and cause a huge burden of social cost.
no code implementations • 31 May 2021 • Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, Dusit Niyato, H. Vincent Poor
The Industrial Internet of Things (IIoT) offers promising opportunities to transform the operation of industrial systems and becomes a key enabler for future industries.
no code implementations • 14 May 2021 • Khalique Newaz, Jacob Piland, Patricia L. Clark, Scott J. Emrich, Jun Li, Tijana Milenkovic
Here, we propose for the first time a way to model 3D structures of proteins as dynamic PSNs, with the hypothesis that this will improve upon the current state-of-the-art PSC approaches that are based on static PSNs (and thus upon the existing state-of-the-art sequence and other 3D structural approaches).
no code implementations • 14 May 2021 • Yusheng Xiang, Kailun Liu, Tianqing Su, Jun Li, Shirui Ouyang, Samuel S. Mao, Marcus Geimer
In the practical implementation of a construction site, it is sensible to solve the problem with a hybrid solution; therefore, in our study, we proposed an algorithm based on a cutting-edge multi-pathfinding algorithm to enable the massive number of machines cooperation and offer the advice to modify the unreasonable part of the working site in the meantime.
1 code implementation • 10 May 2021 • Chuan Ma, Jun Li, Ming Ding, Kang Wei, Wen Chen, H. Vincent Poor
Owing to the low communication costs and privacy-promoting capabilities, Federated Learning (FL) has become a promising tool for training effective machine learning models among distributed clients.
1 code implementation • 1 May 2021 • Lei Yang, Xinyu Zhang, Li Wang, Minghan Zhu, Jun Li
3D object detection with a single image is an essential and challenging task for autonomous driving.
1 code implementation • 29 Apr 2021 • Jun Li, Zhaocong Wu, Zhongwen Hu, Canliang Jian, Shaojie Luo, Lichao Mou, Xiao Xiang Zhu, Matthieu Molinier
In the encoder, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features.
no code implementations • 25 Apr 2021 • Jinping Wang, Xiaojun Tan, JianHuang Lai, Jun Li, Canqun Xiang
Based on this observation, this paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field.
no code implementations • 16 Apr 2021 • Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, H. Vincent Poor
The Internet of Things (IoT) is penetrating many facets of our daily life with the proliferation of intelligent services and applications empowered by artificial intelligence (AI).
no code implementations • 5 Apr 2021 • Lei Xie, Zishu He, Jun Tong, Jun Li, Jiangtao Xi
We propose leave-one-out cross-validation (LOOCV) choices for the shrinkage factors to optimize the beamforming performance, referred to as $\text{S}^2$CM-CV and STE-CV.
no code implementations • CVPR 2021 • Jun Li, Sinisa Todorovic
Our SSL trains an RNN to recognize positive and negative action sequences, and the RNN's hidden layer is taken as our new action-level feature embedding.
no code implementations • 5 Apr 2021 • Dengsheng Chen, Haowen Deng, Jun Li, Duo Li, Yao Duan, Kai Xu
In this work, rather than defining a continuous or discrete kernel, we directly embed convolutional kernels into the learnable potential fields, giving rise to potential convolution.
no code implementations • CVPR 2021 • Jun Li, Sinisa Todorovic
This paper is about action segmentation under weak supervision in training, where the ground truth provides only a set of actions present, but neither their temporal ordering nor when they occur in a training video.
no code implementations • 20 Mar 2021 • Zhenhong Zou, Xinyu Zhang, Huaping Liu, Zhiwei Li, Amir Hussain, Jun Li
There has recently been growing interest in utilizing multimodal sensors to achieve robust lane line segmentation.
no code implementations • 17 Mar 2021 • Lei Xie, Zishu He, Jun Tong, Tianle Liu, Jun Li, Jiangtao Xi
This paper investigates regularized estimation of Kronecker-structured covariance matrices (CM) for polarization radar in sea clutter scenarios where the data are assumed to follow the complex, elliptically symmetric (CES) distributions with a Kronecker-structured CM.
1 code implementation • 15 Mar 2021 • Li Wang, Chenfei Wang, Xinyu Zhang, Tianwei Lan, Jun Li
3D object detection plays a crucial role in environmental perception for autonomous vehicles, which is the prerequisite of decision and control.
no code implementations • 11 Mar 2021 • Chenhaoping Wen, Jingjing Gao, Yuan Xie, Qing Zhang, Pengfei Kong, Jinghui Wang, Yilan Jiang, Xuan Luo, Jun Li, Wenjian Lu, Yu-Ping Sun, Shichao Yan
4$H_{\rm b}$-TaS$_2$ is a superconducting compound with alternating 1$T$-TaS$_2$ and 1$H$-TaS$_2$ layers, where the 1$H$-TaS$_2$ layer has weak charge density wave (CDW) pattern and reduces the CDW coupling between the adjacent 1$T$-TaS$_2$ layers.
Mesoscale and Nanoscale Physics Materials Science
2 code implementations • 10 Mar 2021 • Hainan Li, Renshuai Tao, Jun Li, Haotong Qin, Yifu Ding, Shuo Wang, Xianglong Liu
Self-supervised learning is emerged as an efficient method to utilize unlabeled data.
no code implementations • 3 Feb 2021 • James Mou, Jun Li
Our results show a strong dependency of word accuracy on the Number of Filters of convolutional layers.
no code implementations • 28 Jan 2021 • Kang Wei, Jun Li, Ming Ding, Chuan Ma, Yo-Seb Jeon, H. Vincent Poor
An attacker in FL may control a number of participant clients, and purposely craft the uploaded model parameters to manipulate system outputs, namely, model poisoning (MP).
no code implementations • 21 Jan 2021 • Juncai Pu, Jun Li, Yong Chen
On the bases of the improved method, the effects for different numbers of initial points sampled, residual collocation points sampled, network layers, neurons per hidden layer on the second order genuine rational soliton solution dynamics of the DNLS are considered, and the relevant analysis when the locally adaptive activation function chooses different initial values of scalable parameters are also exhibited in the simulation of the two-order rogue wave solution.
Pattern Formation and Solitons Exactly Solvable and Integrable Systems
no code implementations • 18 Jan 2021 • Jun Li, Yumeng Shao, Kang Wei, Ming Ding, Chuan Ma, Long Shi, Zhu Han, H. Vincent Poor
Focusing on this problem, we explore the impact of lazy clients on the learning performance of BLADE-FL, and characterize the relationship among the optimal K, the learning parameters, and the proportion of lazy clients.
no code implementations • 11 Jan 2021 • Xiaodong Yang, Yunrui Ge, Bo Zhang, Jun Li
High-fidelity control of quantum systems is crucial for quantum information processing, but is often limited by perturbations from the environment and imperfections in the applied control fields.
Quantum Physics
1 code implementation • 16 Dec 2020 • Pengbo Liu, Hu Han, Yuanqi Du, Heqin Zhu, Yinhao Li, Feng Gu, Honghu Xiao, Jun Li, Chunpeng Zhao, Li Xiao, Xinbao Wu, S. Kevin Zhou
Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.
no code implementations • 2 Dec 2020 • Jun Li, Yumeng Shao, Ming Ding, Chuan Ma, Kang Wei, Zhu Han, H. Vincent Poor
The proposed BLADE-FL has a good performance in terms of privacy preservation, tamper resistance, and effective cooperation of learning.
4 code implementations • CVPR 2021 • Xiang Li, Wenhai Wang, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang
Such a property makes the distribution statistics of a bounding box highly correlated to its real localization quality.
Ranked #38 on
Object Detection
on COCO test-dev
no code implementations • 29 Oct 2020 • Jun Li, Lei Chen, Jiajia Chen
Two-step aggregation is introduced to facilitate scalable federated learning (SFL) over passive optical networks (PONs).
Networking and Internet Architecture
no code implementations • 12 Oct 2020 • Zhiyang Lu, Jun Li, Zheng Li, Hongjian He, Jun Shi
In this work, we propose to explore a new value of the high-pass filtered phase data generated in susceptibility weighted imaging (SWI), and develop an end-to-end Cross-connected $\Psi$-Net (C$\Psi$-Net) to reconstruct QSM directly from these phase data in SWI without additional pre-processing.
no code implementations • 20 Sep 2020 • Chuan Ma, Jun Li, Ming Ding, Long Shi, Taotao Wang, Zhu Han, H. Vincent Poor
Motivated by the explosive computing capabilities at end user equipments, as well as the growing privacy concerns over sharing sensitive raw data, a new machine learning paradigm, named federated learning (FL) has emerged.
Networking and Internet Architecture
no code implementations • 1 Sep 2020 • Jun Li, Wanrong Hong, Yusheng Xiang
On the application side, vector fields are an extremely useful type of data in empirical sciences, as well as signal processing, e. g. non-parametric transformations of 3D point clouds using 3D vector fields, the modelling of the fluid flow in earth science, and the modelling of physical fields.
no code implementations • 26 Aug 2020 • Teng Liu, Hong Wang, Bing Lu, Jun Li, Dongpu Cao
Decision-making strategy for autonomous vehicles de-scribes a sequence of driving maneuvers to achieve a certain navigational mission.
1 code implementation • 3 Aug 2020 • Qiao Liu, Xin Li, Zhenyu He, Chenglong Li, Jun Li, Zikun Zhou, Di Yuan, Jing Li, Kai Yang, Nana Fan, Feng Zheng
We evaluate and analyze more than 30 trackers on LSOTB-TIR to provide a series of baselines, and the results show that deep trackers achieve promising performance.
1 code implementation • 4 Jul 2020 • Chuan Ma, Jun Li, Ming Ding, Bo Liu, Kang Wei, Jian Weng, H. Vincent Poor
Generative adversarial network (GAN) has attracted increasing attention recently owing to its impressive ability to generate realistic samples with high privacy protection.
no code implementations • ACL 2020 • Jun Li, Yifan Cao, Jiong Cai, Yong Jiang, Kewei Tu
Unsupervised constituency parsing aims to learn a constituency parser from a training corpus without parse tree annotations.
1 code implementation • 24 Jun 2020 • Dengsheng Chen, Jun Li, Kai Xu
Adding the attention module with a rectified linear unit (ReLU) results in an amplification of positive elements and a suppression of negative ones, both with learned, data-adaptive parameters.
2 code implementations • 24 Jun 2020 • Wei Luo, Hengmin Zhang, Jun Li, Xiu-Shen Wei
We aim to provide a computationally cheap yet effective approach for fine-grained image classification (FGIC) in this letter.
Ranked #7 on
Fine-Grained Image Classification
on Stanford Dogs
6 code implementations • NeurIPS 2020 • Xiang Li, Wenhai Wang, Lijun Wu, Shuo Chen, Xiaolin Hu, Jun Li, Jinhui Tang, Jian Yang
Specifically, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification, and use a vector to represent arbitrary distribution of box locations.
Ranked #77 on
Object Detection
on COCO test-dev
no code implementations • 5 May 2020 • Chandan Pradhan, Ang Li, Lingyang Song, Jun Li, Branka Vucetic, Yonghui Li
In this paper, we focus on the reconfigurable intelligent surface (RIS)-enhanced two-way device-to-device (D2D) multi-pair orthogonal-frequency-division-multiplexing (OFDM) communication systems.
no code implementations • 11 Apr 2020 • Cheng Wang, Kang Wei, Lingjun Kong, Long Shi, Zhen Mei, Jun Li, Kui Cai
The error correcting performance of multi-level-cell (MLC) NAND flash memory is closely related to the block length of error correcting codes (ECCs) and log-likelihood-ratios (LLRs) of the read-voltage thresholds.
1 code implementation • 9 Apr 2020 • Jun Li, Hongfu Liu, Zhiqiang Tao, Handong Zhao, Yun Fu
This paper studies the large-scale subspace clustering (LSSC) problem with million data points.
no code implementations • 23 Mar 2020 • Rui Li, Zach Shahn, Jun Li, Mingyu Lu, Prithwish Chakraborty, Daby Sow, Mohamed Ghalwash, Li-wei H. Lehman
Counterfactual prediction is a fundamental task in decision-making.
no code implementations • 18 Mar 2020 • Yo-Seb Jeon, Mohammad Mohammadi Amiri, Jun Li, H. Vincent Poor
One major challenge in system design is to reconstruct local gradient vectors accurately at the central server, which are computed-and-sent from the wireless devices.
no code implementations • 29 Feb 2020 • Kang Wei, Jun Li, Ming Ding, Chuan Ma, Hang Su, Bo Zhang, H. Vincent Poor
According to our analysis, the UDP framework can realize $(\epsilon_{i}, \delta_{i})$-LDP for the $i$-th MT with adjustable privacy protection levels by varying the variances of the artificial noise processes.
no code implementations • CVPR 2020 • Jun Li, Sinisa Todorovic
This paper is about weakly supervised action segmentation, where the ground truth specifies only a set of actions present in a training video, but not their true temporal ordering.
no code implementations • 22 Feb 2020 • Jun Li, Zhichao Xing, Weibin Zhang, Yan Lin, Feng Shu
Vehicle tracking has become one of the key applications of wireless sensor networks (WSNs) in the fields of rescue, surveillance, traffic monitoring, etc.
no code implementations • 9 Feb 2020 • Yang Zhang, Ivor W. Tsang, Jun Li, Ping Liu, Xiaobo Lu, Xin Yu
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
no code implementations • ICLR 2020 • Jun Li, Li Fuxin, Sinisa Todorovic
We specify two new optimization algorithms: Cayley SGD with momentum, and Cayley ADAM on the Stiefel manifold.
no code implementations • CVPR 2020 • Dengsheng Chen, Jun Li, Zheng Wang, Kai Xu
To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category.
1 code implementation • 15 Jan 2020 • Jaqueline J. Brito, Jun Li, Jason H. Moore, Casey S. Greene, Nicole A. Nogoy, Lana X. Garmire, Serghei Mangul
Computational methods have reshaped the landscape of modern biology.
no code implementations • 3 Jan 2020 • Xiaobo Zhou, Shihao Yan, Min Li, Jun Li, Feng Shu
This work, for the first time, considers confidential data collection in the context of unmanned aerial vehicle (UAV) wireless networks, where the scheduled ground sensor node (SN) intends to transmit confidential information to the UAV without being intercepted by other unscheduled ground SNs.
no code implementations • 9 Dec 2019 • Chenying Liu, Jun Li, Lin He, Antonio J. Plaza, Shutao Li, Bo Li
Specifically, we develop an innovative phase-induced Gabor kernel, which is trickily designed to perform the Gabor feature learning via a linear combination of local low-frequency and high-frequency components of data controlled by the kernel phase.
1 code implementation • NeurIPS 2019 • Shuo Chen, Lei Luo, Jian Yang, Chen Gong, Jun Li, Heng Huang
To address this issue, we first reveal that the traditional linear distance metric is equivalent to the cumulative arc length between the data pair's nearest points on the learned straight measurer lines.
no code implementations • 27 Nov 2019 • Gan Sun, Yang Cong, Qianqian Wang, Jun Li, Yun Fu
As a new spectral clustering task arrives, L2SC firstly transfers knowledge from both basis library and feature library to obtain encoding matrix, and further redefines the library base over time to maximize performance across all the clustering tasks.
no code implementations • 25 Nov 2019 • Jun Li, Tian-Jun Li, Weiwei Wu
For $(\mathbb{C} P^2 \# 5{\overline {\mathbb{C} P^2}},\omega)$, let $N_{\omega}$ be the number of $(-2)$-symplectic spherical homology classes. We completely determine the Torelli symplectic mapping class group (Torelli SMCG): the Torelli SMCG is trivial if $N_{\omega}>8$; it is $\pi_0(Diff^+(S^2, 5))$ if $N_{\omega}=0$ (by Paul Seidel and Jonathan Evans); it is $\pi_0(Diff^+(S^2, 4))$ in the remaining case.
Symplectic Geometry
no code implementations • 1 Nov 2019 • Kang Wei, Jun Li, Ming Ding, Chuan Ma, Howard H. Yang, Farokhi Farhad, Shi Jin, Tony Q. S. Quek, H. Vincent Poor
Specifically, the theoretical bound reveals the following three key properties: 1) There is a tradeoff between the convergence performance and privacy protection levels, i. e., a better convergence performance leads to a lower protection level; 2) Given a fixed privacy protection level, increasing the number $N$ of overall clients participating in FL can improve the convergence performance; 3) There is an optimal number of maximum aggregation times (communication rounds) in terms of convergence performance for a given protection level.
no code implementations • 25 Oct 2019 • Bin Sun, Jun Li, Ming Shao, Yun Fu
To reduce the computation and memory costs, we propose a novel lightweight deep learning module by low-rank pointwise residual (LPR) convolution, called LPRNet.
no code implementations • 24 Oct 2019 • Jun Li, Xiaoman Shen, Lei Chen, Jiajia Chen
Bandwidth slicing is introduced to support federated learning in edge computing to assure low communication delay for training traffic.
no code implementations • 7 Oct 2019 • Hongyu Guo, Khalique Newaz, Scott Emrich, Tijana Milenkovic, Jun Li
We develop a weighted network that depicts the protein structures, and more importantly, we propose the first graphlet-based measure that applies to weighted networks.
1 code implementation • ICCV 2019 • Jun Li, Peng Lei, Sinisa Todorovic
This paper is about labeling video frames with action classes under weak supervision in training, where we have access to a temporal ordering of actions, but their start and end frames in training videos are unknown.
1 code implementation • 17 Sep 2019 • Zixuan Song, Jun Li
Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability.
no code implementations • 14 Sep 2019 • Chuan Ma, Jun Li, Ming Ding, Howard Hao Yang, Feng Shu, Tony Q. S. Quek, H. Vincent Poor
Motivated by the advancing computational capacity of wireless end-user equipment (UE), as well as the increasing concerns about sharing private data, a new machine learning (ML) paradigm has emerged, namely federated learning (FL).
Networking and Internet Architecture
no code implementations • ICCV 2019 • Wei Luo, Xitong Yang, Xianjie Mo, Yuheng Lu, Larry S. Davis, Jun Li, Jian Yang, Ser-Nam Lim
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
Ranked #9 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Visual Categorization
no code implementations • Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19) 2019 • Jun Li, Yongjun Chen, Lei Cai, Ian Davidson, Shuiwang Ji
The proposed dense transformer modules are differentiable, thus the entire network can be trained.
Ranked #1 on
Electron Microscopy Image Segmentation
on SNEMI3D
Electron Microscopy Image Segmentation
Semantic Segmentation
no code implementations • 16 Jun 2019 • Jun Li, Chengjie Niu, Kai Xu
Enlightened by the fact that 3D shape structure is characterized as part composition and placement, we propose to model 3D shape variations with a part-aware deep generative network, coined as PAGENet.
no code implementations • 11 May 2019 • Jun Li, Xun Lin, Xiaoguang Rui, Yong Rui, DaCheng Tao
Distance metric learning is successful in discovering intrinsic relations in data.
1 code implementation • 13 Apr 2019 • Guoliang Kang, Jun Li, DaCheng Tao
Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training.
no code implementations • 3 Mar 2019 • Jun Li, Xiaozhu Lin, Hui Che, Hao Li, Xiaohua Qian
To alleviate these problems, we propose a probabilistic-map-guided bi-directional recurrent UNet (PBR-UNet) architecture, which fuses intra-slice information and inter-slice probabilistic maps into a local 3D hybrid regularization scheme, which is followed by bi-directional recurrent network optimization.
no code implementations • 3 Mar 2019 • Hao Li, Jun Li, Xiaozhu Lin, Xiaohua Qian
The irregular geometry and high inter-slice variability in computerized tomography (CT) scans of the human pancreas make an accurate segmentation of this crucial organ a challenging task for existing data-driven deep learning methods.
no code implementations • 24 Feb 2019 • Sina Shaham, Ming Ding, Bo Liu, Shuping Dang, Zihuai Lin, Jun Li
By introducing a new formulation of the problem, we are able to apply machine learning algorithms for clustering the trajectories and propose to use $k$-means algorithm for this purpose.
no code implementations • 21 Feb 2019 • Jun Li, Daoyu Lin, Yang Wang, Guangluan Xu, Chibiao Ding
However, most recent approaches to remote sensing scene classification are based on Convolutional Neural Networks (CNNs).
no code implementations • 8 Oct 2018 • Ancheng Lin, Jun Li, Zhenyuan Ma
In this work, we investigate the following: 1) how the routing affects the CapsNet model fitting; 2) how the representation using capsules helps discover global structures in data distribution, and; 3) how the learned data representation adapts and generalizes to new tasks.
no code implementations • 27 Sep 2018 • Guoshuai Zhao, Jun Li, Lu Wang, Xueming Qian, Yun Fu
In this paper, we propose a Graph-Sequence-to-Sequence(GraphSeq2Seq) model to fuse the dependency graph among words into the traditional Seq2Seq framework.
1 code implementation • IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium 2018 • Sheng-Jie Liu, Haowen Luo, Ying Tu, Zhi He, Jun Li
As it is very difficult and expensive to obtain class labels in real world, we integrate the proposed WCRN with AL to improve its generalization by using the most informative training samples.
no code implementations • 10 Jun 2018 • Yiqi Yan, Lei Zhang, Jun Li, Wei Wei, Yanning Zhang
Different from traditional hyperspectral super-resolution approaches that focus on improving the spatial resolution, spectral super-resolution aims at producing a high-resolution hyperspectral image from the RGB observation with super-resolution in spectral domain.
no code implementations • ICLR 2019 • Jun Li, Hongfu Liu, Bineng Zhong, Yue Wu, Yun Fu
To address this problem, we propose a simple yet effective method for improving stochastic gradient methods named predictive local smoothness (PLS).
no code implementations • 16 May 2018 • Sina Shaham, Ming Ding, Bo Liu, Zihuai Lin, Jun Li
In this paper, we incorporate a new type of side information based on consecutive location changes of users and propose a new metric called transition-entropy to investigate the location privacy preservation, followed by two algorithms to improve the transition-entropy for a given dummy generation algorithm.
no code implementations • 26 Apr 2018 • Jia Liu, Yu Lei, Yan Ke, Jun Li, Min-qing Zhang, Xiaoyuan Yan
In this paper, a new data-driven information hiding scheme called generative steganography by sampling (GSS) is proposed.
no code implementations • CVPR 2018 • Chengjie Niu, Jun Li, Kai Xu
We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry.
1 code implementation • 5 Mar 2018 • Panpan Zheng, Shuhan Yuan, Xintao Wu, Jun Li, Aidong Lu
Currently, most of the fraud detection approaches require a training dataset that contains records of both benign and malicious users.
no code implementations • 9 Feb 2018 • Shuo Chen, Chen Gong, Jian Yang, Xiang Li, Yang Wei, Jun Li
In distinguishment stage, a metric is exhaustively learned to try its best to distinguish both the adversarial pairs and the original training pairs.
no code implementations • 5 Jan 2018 • Hongfu Liu, Jun Li, Yue Wu, Yun Fu
Then an objective function based Holoentropy is designed to enhance the compactness of each cluster with a few outliers removed.
4 code implementations • 4 Jan 2018 • Xi-Wei Yao, Hengyan Wang, Zeyang Liao, Ming-Cheng Chen, Jian Pan, Jun Li, Kechao Zhang, Xingcheng Lin, Zhehui Wang, Zhihuang Luo, Wenqiang Zheng, Jianzhong Li, Meisheng Zhao, Xinhua Peng, Dieter Suter
Processing of digital images is continuously gaining in volume and relevance, with concomitant demands on data storage, transmission and processing power.
Quantum Physics
no code implementations • 3 Jun 2017 • Shuhan Yuan, Xintao Wu, Jun Li, Aidong Lu
Due to the small dimension of spectral coordinates (compared with the dimension of the adjacency matrix derived from a graph), training deep neural networks becomes feasible.
1 code implementation • 24 May 2017 • Jun Li, Yongjun Chen, Lei Cai, Ian Davidson, Shuiwang Ji
The proposed dense transformer modules are differentiable, thus the entire network can be trained.
no code implementations • 5 May 2017 • Jun Li, Kai Xu, Siddhartha Chaudhuri, Ersin Yumer, Hao Zhang, Leonidas Guibas
We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures.
no code implementations • ICCV 2017 • Jun Li, Reinhard Klein, Angela Yao
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem.
Ranked #34 on
Monocular Depth Estimation
on NYU-Depth V2
no code implementations • CVPR 2016 • Zhang Zhang, Kaiqi Huang, Tieniu Tan, Peipei Yang, Jun Li
For spectral embedding/clustering, it is still an open problem on how to construct an relation graph to reflect the intrinsic structures in data.
no code implementations • 29 Apr 2016 • Biyun Sheng, Chunhua Shen, Guosheng Lin, Jun Li, Wankou Yang, Changyin Sun
Crowd counting is an important task in computer vision, which has many applications in video surveillance.
no code implementations • 5 Jan 2015 • Jun Li, Heyou Chang, Jian Yang
Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference.
no code implementations • 20 Dec 2013 • Jun Li, Wei Luo, Jian Yang, Xiao-Tong Yuan
It is well known that direct training of deep neural networks will generally lead to poor results.