Search Results for author: Kai Zhang

Found 75 papers, 32 papers with code

An Adaptive Neuro-Fuzzy System with Integrated Feature Selection and Rule Extraction for High-Dimensional Classification Problems

no code implementations10 Jan 2022 Guangdong Xue, Qin Chang, Jian Wang, Kai Zhang, Nikhil R. Pal

The effectiveness of the FSRE-AdaTSK is demonstrated on 19 datasets of which five are in more than 2000 dimension including two with dimension greater than 7000.

Gendered Differences in Face Recognition Accuracy Explained by Hairstyles, Makeup, and Facial Morphology

no code implementations29 Dec 2021 Vítor Albiero, Kai Zhang, Michael C. King, Kevin W. Bowyer

There is consensus in the research literature that face recognition accuracy is lower for females, who often have both a higher false match rate and a higher false non-match rate.

Face Recognition

Scalable Causal Structure Learning: New Opportunities in Biomedicine

no code implementations15 Oct 2021 Pulakesh Upadhyaya, Kai Zhang, Can Li, Xiaoqian Jiang, Yejin Kim

This paper gives a practical tutorial on popular causal structure learning models with examples of real-world data to help healthcare audiences understand and apply them.

Towards Flexible Blind JPEG Artifacts Removal

1 code implementation ICCV 2021 Jiaxi Jiang, Kai Zhang, Radu Timofte

Training a single deep blind model to handle different quality factors for JPEG image artifacts removal has been attracting considerable attention due to its convenience for practical usage.

Image Compression Image Compression Artifact Reduction +5

GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks

no code implementations EMNLP 2021 Weicheng Ma, Renze Lou, Kai Zhang, Lili Wang, Soroush Vosoughi

Compared to AUTOSEM, a strong baseline method, GradTS improves the performance of MT-DNN with a bert-base-cased backend model, from 0. 33% to 17. 93% on 8 natural language understanding (NLU) tasks in the GLUE benchmarks.

Multi-Task Learning Natural Language Understanding

A Fast PC Algorithm with Reversed-order Pruning and A Parallelization Strategy

no code implementations10 Sep 2021 Kai Zhang, Chao Tian, Kun Zhang, Todd Johnson, Xiaoqian Jiang

The PC algorithm is the state-of-the-art algorithm for causal structure discovery on observational data.

SwinIR: Image Restoration Using Swin Transformer

3 code implementations23 Aug 2021 Jingyun Liang, JieZhang Cao, Guolei Sun, Kai Zhang, Luc van Gool, Radu Timofte

In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.

Color Image Denoising Image Denoising +4

Learning to Detect: A Data-driven Approach for Network Intrusion Detection

no code implementations18 Aug 2021 Zachary Tauscher, Yushan Jiang, Kai Zhang, Jian Wang, Houbing Song

With massive data being generated daily and the ever-increasing interconnectivity of the world's Internet infrastructures, a machine learning based intrusion detection system (IDS) has become a vital component to protect our economic and national security.

Network Intrusion Detection Representation Learning

Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks

no code implementations ACL 2021 Weicheng Ma, Kai Zhang, Renze Lou, Lili Wang, Soroush Vosoughi

Through extensive experiments, we show that (1) pruning a number of attention heads in a multi-lingual Transformer-based model has, in general, positive effects on its performance in cross-lingual and multi-lingual tasks and (2) the attention heads to be pruned can be ranked using gradients and identified with a few trial experiments.

Federated Variational Learning for Anomaly Detection in Multivariate Time Series

no code implementations18 Aug 2021 Kai Zhang, Yushan Jiang, Lee Seversky, Chengtao Xu, Dahai Liu, Houbing Song

Anomaly detection has been a challenging task given high-dimensional multivariate time series data generated by networked sensors and actuators in Cyber-Physical Systems (CPS).

Anomaly Detection Representation Learning +1

SIFN: A Sentiment-aware Interactive Fusion Network for Review-based Item Recommendation

no code implementations18 Aug 2021 Kai Zhang, Hao Qian, Qi Liu, Zhiqiang Zhang, Jun Zhou, Jianhui Ma, Enhong Chen

Specifically, we first encode user/item reviews via BERT and propose a light-weighted sentiment learner to extract semantic features of each review.

Recommendation Systems

Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling

1 code implementation ICCV 2021 Jingyun Liang, Andreas Lugmayr, Kai Zhang, Martin Danelljan, Luc van Gool, Radu Timofte

More specifically, HCFlow learns a bijective mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously.

Image Super-Resolution

Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution

1 code implementation ICCV 2021 Jingyun Liang, Guolei Sun, Kai Zhang, Luc van Gool, Radu Timofte

Extensive experiments on synthetic and real images show that the proposed MANet not only performs favorably for both spatially variant and invariant kernel estimation, but also leads to state-of-the-art blind SR performance when combined with non-blind SR methods.

Affine Transformation Image Super-Resolution

Video Super-Resolution Transformer

1 code implementation12 Jun 2021 JieZhang Cao, Yawei Li, Kai Zhang, Luc van Gool

Specifically, to tackle the first issue, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information.

Optical Flow Estimation Video Super-Resolution

Open Hierarchical Relation Extraction

1 code implementation NAACL 2021 Kai Zhang, Yuan YAO, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

To establish the bidirectional connections between OpenRE and relation hierarchy, we propose the task of open hierarchical relation extraction and present a novel OHRE framework for the task.

Relation Extraction

LocalViT: Bringing Locality to Vision Transformers

2 code implementations12 Apr 2021 Yawei Li, Kai Zhang, JieZhang Cao, Radu Timofte, Luc van Gool

The importance of locality mechanisms is validated in two ways: 1) A wide range of design choices (activation function, layer placement, expansion ratio) are available for incorporating locality mechanisms and all proper choices can lead to a performance gain over the baseline, and 2) The same locality mechanism is successfully applied to 4 vision transformers, which shows the generalization of the locality concept.

Image Classification

PQA: Perceptual Question Answering

1 code implementation CVPR 2021 Yonggang Qi, Kai Zhang, Aneeshan Sain, Yi-Zhe Song

Perceptual organization remains one of the very few established theories on the human visual system.

Question Answering

PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting

no code implementations CVPR 2021 Kai Zhang, Fujun Luan, Qianqian Wang, Kavita Bala, Noah Snavely

We present PhySG, an end-to-end inverse rendering pipeline that includes a fully differentiable renderer and can reconstruct geometry, materials, and illumination from scratch from a set of RGB input images.

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution

1 code implementation ICCV 2021 Kai Zhang, Jingyun Liang, Luc van Gool, Radu Timofte

It is widely acknowledged that single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images.

Image Super-Resolution

Spatio-Temporal Data Mining for Aviation Delay Prediction

no code implementations20 Mar 2021 Kai Zhang, Yushan Jiang, Dahai Liu, Houbing Song

A key role of collaborative decision making for air traffic scheduling and airspace resource management is the accurate prediction of flight delay.

Decision Making

Local Change Point Detection and Signal Cleaning using EEMD with applications to Acoustic Shockwaves

no code implementations1 Mar 2021 Kentaro Hoffman, Jonathan M. Lees, Kai Zhang

Using this technique, we demonstrate improved signal cleaning performance for acoustic shockwave signal detection.

Change Point Detection


no code implementations1 Mar 2021 Kai Zhang, Zhigen Zhao, Wen Zhou

To achieve a robust power, we study test statistics with data-adaptive weights, referred to as the binary expansion adaptive symmetry test (BEAST).

RpBERT: A Text-image Relation Propagation-based BERT Model for Multimodal NER

1 code implementation5 Feb 2021 Lin Sun, Jiquan Wang, Kai Zhang, Yindu Su, Fangsheng Weng

We integrate soft or hard gates to select visual clues and propose a multitask algorithm to train on the MNER datasets.

Named Entity Recognition NER

Real-time Prediction for Mechanical Ventilation in COVID-19 Patients using A Multi-task Gaussian Process Multi-objective Self-attention Network

no code implementations1 Feb 2021 Kai Zhang, Siddharth Karanth, Bela Patel, Robert Murphy, Xiaoqian Jiang

We propose a novel in-time risk trajectory predictive model to handle the irregular sampling rate in the data, which follows the dynamics of risk of performing mechanical ventilation for individual patients.

Trajectory Prediction

Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization

no code implementations7 Jan 2021 Masaki Morimoto, Kai Fukami, Kai Zhang, Aditya G. Nair, Koji Fukagata

We then discuss the influence of various parameters and operations on the CNN performance, with the utilization of autoencoder (AE).

Dimensionality Reduction Fluid Dynamics Computational Physics

Nanoscale spin detection of copper ions using double electron-electron resonance at room temperature

no code implementations7 Jan 2021 Kai Zhang, Shreya Ghosh, Sunil Saxena, M. V. Gurudev Dutt

We report the nanoscale spin detection and electron paramagnetic resonance (EPR) spectrum of copper (Cu$^{2+}$) ions via double electron-electron resonance with single spins in diamond at room temperature and low magnetic fields.

Quantum Physics Mesoscale and Nanoscale Physics

Kinetic Energy Distribution of Fragments for Thermal Neutron-Induced $^{235}$U and $^{239}$Pu Fission Reactions

no code implementations24 Dec 2020 Xiaojun Sun, Haiyuan Peng, Liying Xie, Kai Zhang, Yan Liang, Yinlu Han, Nengchuan Su, Jie Yan, Jun Xiao, Junjie Sun

(2) Every complementary pair of the primary fission fragments is approximatively described as two ellipsoids with large deformation at scission moment.

Nuclear Theory

SDSS-IV/MaNGA: Can impulsive gaseous inflows explain steep oxygen abundance profiles \& anomalously-low-metallicity regions?

no code implementations23 Dec 2020 Zachary J. Pace, Christy Tremonti, Adam L. Schaefer, David V. Stark, Catherine A. Witherspoon, Karen L. Masters, Niv Drory, Kai Zhang

We reveal a mutual correlation between steep oxygen abundance profiles between $0. 25-1. 5 R_e$, increased variability of metallicity between $1. 25-1. 75 R_e$, and elevated HI content at fixed total galaxy stellar mass.

Astrophysics of Galaxies

Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction

no code implementations13 Dec 2020 Kai Zhang, Hao Qian, Qing Cui, Qi Liu, Longfei Li, Jun Zhou, Jianhui Ma, Enhong Chen

In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature.

Click-Through Rate Prediction

NeRF++: Analyzing and Improving Neural Radiance Fields

3 code implementations15 Oct 2020 Kai Zhang, Gernot Riegler, Noah Snavely, Vladlen Koltun

Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes.

Cascaded Semantic and Positional Self-Attention Network for Document Classification

no code implementations Findings of the Association for Computational Linguistics 2020 Juyong Jiang, Jie Zhang, Kai Zhang

In this work, we propose a new architecture to aggregate the two sources of information using cascaded semantic and positional self-attention network (CSPAN) in the context of document classification.

Document Classification General Classification +1

Plug-and-Play Image Restoration with Deep Denoiser Prior

4 code implementations31 Aug 2020 Kai Zhang, Yawei Li, WangMeng Zuo, Lei Zhang, Luc van Gool, Radu Timofte

Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems.

Deblurring Demosaicking +1

The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures

1 code implementation CVPR 2021 Yawei Li, Wen Li, Martin Danelljan, Kai Zhang, Shuhang Gu, Luc van Gool, Radu Timofte

Based on that, we articulate the heterogeneity hypothesis: with the same training protocol, there exists a layer-wise differentiated network architecture (LW-DNA) that can outperform the original network with regular channel configurations but with a lower level of model complexity.

Image Classification Image Restoration +1

Learning Context-Based Non-local Entropy Modeling for Image Compression

no code implementations10 May 2020 Mu Li, Kai Zhang, WangMeng Zuo, Radu Timofte, David Zhang

To address this issue, we propose a non-local operation for context modeling by employing the global similarity within the context.

Image Compression

Adaptive Structural Fingerprints for Graph Attention Networks

no code implementations ICLR 2020 Kai Zhang, Yaokang Zhu, Jun Wang, Jie Zhang

Yet, how to fully exploit rich structural information in the attention mechanism remains a challenge.

Graph Attention

Depth Sensing Beyond LiDAR Range

no code implementations CVPR 2020 Kai Zhang, Jiaxin Xie, Noah Snavely, Qifeng Chen

Depth sensing is a critical component of autonomous driving technologies, but today's LiDAR- or stereo camera-based solutions have limited range.

Autonomous Driving

A Method for Curation of Web-Scraped Face Image Datasets

2 code implementations7 Apr 2020 Kai Zhang, Vítor Albiero, Kevin W. Bowyer

The numbers of subjects and images acquired in web-scraped datasets are usually very large, with number of images on the millions scale.

Face Recognition

Computational Performance of a Germline Variant Calling Pipeline for Next Generation Sequencing

no code implementations1 Apr 2020 Jie Liu, Xiaotian Wu, Kai Zhang, Bing Liu, Renyi Bao, Xiao Chen, Yiran Cai, Yiming Shen, Xinjun He, Jun Yan, Weixing Ji

With the booming of next generation sequencing technology and its implementation in clinical practice and life science research, the need for faster and more efficient data analysis methods becomes pressing in the field of sequencing.

DHP: Differentiable Meta Pruning via HyperNetworks

2 code implementations ECCV 2020 Yawei Li, Shuhang Gu, Kai Zhang, Luc van Gool, Radu Timofte

Passing the sparsified latent vectors through the hypernetworks, the corresponding slices of the generated weight parameters can be removed, achieving the effect of network pruning.

Denoising Image Classification +3

Deep Unfolding Network for Image Super-Resolution

1 code implementation CVPR 2020 Kai Zhang, Luc van Gool, Radu Timofte

As a result, the proposed network inherits the flexibility of model-based methods to super-resolve blurry, noisy images for different scale factors via a single model, while maintaining the advantages of learning-based methods.

Image Super-Resolution

How Does Gender Balance In Training Data Affect Face Recognition Accuracy?

1 code implementation7 Feb 2020 Vítor Albiero, Kai Zhang, Kevin W. Bowyer

Deep learning methods have greatly increased the accuracy of face recognition, but an old problem still persists: accuracy is usually higher for men than women.

Face Recognition

Analysis of Gender Inequality In Face Recognition Accuracy

no code implementations31 Jan 2020 Vítor Albiero, Krishnapriya K. S., Kushal Vangara, Kai Zhang, Michael C. King, Kevin W. Bowyer

We show that the female genuine distribution improves when only female images without facial cosmetics are used, but that the female impostor distribution also degrades at the same time.

Face Recognition

The Binary Expansion Randomized Ensemble Test (BERET)

no code implementations8 Dec 2019 Duyeol Lee, Kai Zhang, Michael R. Kosorok

Recently, the binary expansion testing framework was introduced to test the independence of two continuous random variables by utilizing symmetry statistics that are complete sufficient statistics for dependence.

Exploring Overall Contextual Information for Image Captioning in Human-Like Cognitive Style

no code implementations ICCV 2019 Hongwei Ge, Zehang Yan, Kai Zhang, Mingde Zhao, Liang Sun

In the training process, the forward and backward LSTMs encode the succeeding and preceding words into their respective hidden states by simultaneously constructing the whole sentence in a complementary manner.

Image Captioning

Leveraging Vision Reconstruction Pipelines for Satellite Imagery

no code implementations7 Oct 2019 Kai Zhang, Jin Sun, Noah Snavely

Reconstructing 3D geometry from satellite imagery is an important topic of research.

3D Reconstruction

Neural Blind Deconvolution Using Deep Priors

1 code implementation CVPR 2020 Dongwei Ren, Kai Zhang, Qilong Wang, QinGhua Hu, WangMeng Zuo

To connect MAP and deep models, we in this paper present two generative networks for respectively modeling the deep priors of clean image and blur kernel, and propose an unconstrained neural optimization solution to blind deconvolution.

Deblurring Self-Supervised Learning

A Convolutional Forward and Back-Projection Model for Fan-Beam Geometry

no code implementations24 Jul 2019 Kai Zhang, Alireza Entezari

Iterative methods for tomographic image reconstruction have great potential for enabling high quality imaging from low-dose projection data.

Image Reconstruction

TOI-CNN: a Solution of Information Extraction on Chinese Insurance Policy

no code implementations NAACL 2019 Lin Sun, Kai Zhang, Fule Ji, Zhenhua Yang

The advantage of TOI pooling layer is that the nested elements from one sentence could share computation and context in the forward and backward passes.

A Reference Vector based Many-Objective Evolutionary Algorithm with Feasibility-aware Adaptation

no code implementations12 Apr 2019 Mingde Zhao, Hongwei Ge, Kai Zhang, Yaqing Hou

The infeasible parts of the objective space in difficult many-objective optimization problems cause trouble for evolutionary algorithms.

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels

1 code implementation CVPR 2019 Kai Zhang, WangMeng Zuo, Lei Zhang

In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help of plug-and-play framework to handle LR images with arbitrary blur kernels.

Deblurring Image Restoration +1

Generalizable Meta-Heuristic based on Temporal Estimation of Rewards for Large Scale Blackbox Optimization

no code implementations17 Dec 2018 Mingde Zhao, Hongwei Ge, Yi Lian, Kai Zhang

The generalization abilities of heuristic optimizers may deteriorate with the increment of the search space dimensionality.

Multi-Armed Bandits

Toward Convolutional Blind Denoising of Real Photographs

2 code implementations CVPR 2019 Shi Guo, Zifei Yan, Kai Zhang, WangMeng Zuo, Lei Zhang

While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs.

Image Denoising Noise Estimation

Multi-level Wavelet-CNN for Image Restoration

5 code implementations18 May 2018 Pengju Liu, Hongzhi Zhang, Kai Zhang, Liang Lin, WangMeng Zuo

With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork.

Image Denoising Image Super-Resolution +1

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

1 code implementation CVPR 2018 Kai Zhang, WangMeng Zuo, Lei Zhang

Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR).

Image Super-Resolution

FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising

5 code implementations11 Oct 2017 Kai Zhang, WangMeng Zuo, Lei Zhang

Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising.

Image Denoising

Learning Deep CNN Denoiser Prior for Image Restoration

1 code implementation CVPR 2017 Kai Zhang, WangMeng Zuo, Shuhang Gu, Lei Zhang

Recent works have revealed that, with the aid of variable splitting techniques, denoiser prior can be plugged in as a modular part of model-based optimization methods to solve other inverse problems (e. g., deblurring).

Color Image Denoising Deblurring +2

Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network

no code implementations23 Mar 2017 Yudong Liang, Ze Yang, Kai Zhang, Yihui He, Jinjun Wang, Nanning Zheng

To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed.

Image Super-Resolution SSIM

BET on Independence

no code implementations17 Oct 2016 Kai Zhang

To avoid such power loss, we approach the nonparametric test of independence through the new framework of binary expansion statistics (BEStat) and binary expansion testing (BET), which examine dependence through a novel binary expansion filtration approximation of the copula.

Entity Embedding-based Anomaly Detection for Heterogeneous Categorical Events

no code implementations26 Aug 2016 Ting Chen, Lu-An Tang, Yizhou Sun, Zhengzhang Chen, Kai Zhang

Anomaly detection plays an important role in modern data-driven security applications, such as detecting suspicious access to a socket from a process.

Anomaly Detection

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

14 code implementations13 Aug 2016 Kai Zhang, WangMeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang

Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance.

Image Deblocking Image Denoising +2

Seeing the Forest from the Trees in Two Looks: Matrix Sketching by Cascaded Bilateral Sampling

no code implementations25 Jul 2016 Kai Zhang, Chuanren Liu, Jie Zhang, Hui Xiong, Eric Xing, Jieping Ye

Given a matrix A of size m by n, state-of-the-art randomized algorithms take O(m * n) time and space to obtain its low-rank decomposition.

Ranking Causal Anomalies via Temporal and Dynamical Analysis on Vanishing Correlations

1 code implementation ACM SIGKDD international conference on Knowledge discovery and data mining 2016 Wei Cheng, Kai Zhang, Haifeng Chen, Guofei Jiang, Zhengzhang Chen, Wei Wang

Structures and evolutions of the invariance network, in particular the vanishing correlations, can shed important light on locating causal anomalies and performing diagnosis.

Spherical Cap Packing Asymptotics and Rank-Extreme Detection

no code implementations19 Nov 2015 Kai Zhang

Such probabilistic considerations result in an asymptotic sharp universal uniform bound on the maximal inner product between any set of unit vectors and a stochastically independent uniformly distributed unit vector.

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