Search Results for author: Kai Zhang

Found 185 papers, 88 papers with code

Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation

1 code implementation27 Feb 2024 Yuankai Fan, Zhenying He, Tonghui Ren, Can Huang, Yinan Jing, Kai Zhang, X. Sean Wang

While these translation models have greatly improved the overall translation accuracy, surpassing 70% on NLIDB benchmarks, the use of auto-regressive decoding to generate single SQL queries may result in sub-optimal outputs, potentially leading to erroneous translations.

Learning-To-Rank Translation

A Neural-network Enhanced Video Coding Framework beyond ECM

no code implementations13 Feb 2024 Yanchen Zhao, Wenxuan He, Chuanmin Jia, Qizhe Wang, Junru Li, Yue Li, Chaoyi Lin, Kai Zhang, Li Zhang, Siwei Ma

In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies.

Video Compression

TravelPlanner: A Benchmark for Real-World Planning with Language Agents

1 code implementation2 Feb 2024 Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, Yu Su

Are these language agents capable of planning in more complex settings that are out of the reach of prior AI agents?

LVC-LGMC: Joint Local and Global Motion Compensation for Learned Video Compression

no code implementations1 Feb 2024 Wei Jiang, Junru Li, Kai Zhang, Li Zhang

To validate the effectiveness of our proposed LGMC, we integrate it with DCVC-TCM and obtain learned video compression with joint local and global motion compensation (LVC-LGMC).

Motion Compensation Video Compression

Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning

1 code implementation31 Jan 2024 Tinghui Zhu, Kai Zhang, Jian Xie, Yu Su

Recent advancements have significantly augmented the reasoning capabilities of Large Language Models (LLMs) through various methodologies, especially chain-of-thought (CoT) reasoning.

LKFormer: Large Kernel Transformer for Infrared Image Super-Resolution

1 code implementation22 Jan 2024 Feiwei Qin, Kang Yan, Changmiao Wang, Ruiquan Ge, Yong Peng, Kai Zhang

Given the broad application of infrared technology across diverse fields, there is an increasing emphasis on investigating super-resolution techniques for infrared images within the realm of deep learning.

Image Super-Resolution Infrared image super-resolution

Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting

1 code implementation17 Jan 2024 Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepulveda, Yixing Lao, Kai Zhang, Tianhang Cheng, Stephan Richter, Shenlong Wang, German Ros

Reconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also to the new lighting conditions and yet evaluations of inverse rendering methods rely on novel view synthesis data or simplistic synthetic datasets for quantitative analysis.

Inverse Rendering Novel View Synthesis

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model

no code implementations10 Jan 2024 Yinghui Xing, Litao Qu, Shizhou Zhang, Kai Zhang, Yanning Zhang

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution.

Pansharpening

GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation

1 code implementation8 Jan 2024 Tong Wu, Guandao Yang, Zhibing Li, Kai Zhang, Ziwei Liu, Leonidas Guibas, Dahua Lin, Gordon Wetzstein

These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences.

Text to 3D

UMIE: Unified Multimodal Information Extraction with Instruction Tuning

1 code implementation5 Jan 2024 Lin Sun, Kai Zhang, Qingyuan Li, Renze Lou

Multimodal information extraction (MIE) gains significant attention as the popularity of multimedia content increases.

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following

no code implementations5 Dec 2023 Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, Hanzi Xu, Yu Su, Wenpeng Yin

In the realm of large language models (LLMs), enhancing instruction-following capability often involves curating expansive training data.

Instruction Following

Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts

no code implementations3 Dec 2023 Eashan Adhikarla, Kai Zhang, Jun Yu, Lichao Sun, John Nicholson, Brian D. Davison

As a result, it raises concerns about the overall robustness of the machine learning techniques for computer vision applications that are deployed publicly for consumers.

Data Augmentation Transfer Learning

Deep Equilibrium Diffusion Restoration with Parallel Sampling

1 code implementation20 Nov 2023 JieZhang Cao, Yue Shi, Kai Zhang, Yulun Zhang, Radu Timofte, Luc van Gool

Due to the inherent property of diffusion models, most of these methods need long serial sampling chains to restore HQ images step-by-step.

Image Restoration

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

no code implementations20 Nov 2023 Peng Wang, Hao Tan, Sai Bi, Yinghao Xu, Fujun Luan, Kalyan Sunkavalli, Wenping Wang, Zexiang Xu, Kai Zhang

We propose a Pose-Free Large Reconstruction Model (PF-LRM) for reconstructing a 3D object from a few unposed images even with little visual overlap, while simultaneously estimating the relative camera poses in ~1. 3 seconds on a single A100 GPU.

3D Reconstruction Image to 3D +1

DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model

no code implementations19 Nov 2023 Zhenghao Pan, Haijin Zeng, JieZhang Cao, Kai Zhang, Yongyong Chen

Specifically, firstly, we employ a pre-trained diffusion model, which has been trained on a substantial corpus of RGB images, as the generative denoiser within the Plug-and-Play framework for the first time.

Denoising

MoVideo: Motion-Aware Video Generation with Diffusion Models

no code implementations19 Nov 2023 Jingyun Liang, Yuchen Fan, Kai Zhang, Radu Timofte, Luc van Gool, Rakesh Ranjan

While recent years have witnessed great progress on using diffusion models for video generation, most of them are simple extensions of image generation frameworks, which fail to explicitly consider one of the key differences between videos and images, i. e., motion.

Image Generation Image to Video Generation +1

DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model

no code implementations15 Nov 2023 Yinghao Xu, Hao Tan, Fujun Luan, Sai Bi, Peng Wang, Jiahao Li, Zifan Shi, Kalyan Sunkavalli, Gordon Wetzstein, Zexiang Xu, Kai Zhang

We propose \textbf{DMV3D}, a novel 3D generation approach that uses a transformer-based 3D large reconstruction model to denoise multi-view diffusion.

Denoising Image Reconstruction +1

LRM: Large Reconstruction Model for Single Image to 3D

1 code implementation8 Nov 2023 Yicong Hong, Kai Zhang, Jiuxiang Gu, Sai Bi, Yang Zhou, Difan Liu, Feng Liu, Kalyan Sunkavalli, Trung Bui, Hao Tan

We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds.

Image to 3D

CDR-Adapter: Learning Adapters to Dig Out More Transferring Ability for Cross-Domain Recommendation Models

no code implementations4 Nov 2023 Yanyu Chen, Yao Yao, Wai Kin Victor Chan, Li Xiao, Kai Zhang, Liang Zhang, Yun Ye

In this paper, we present a scalable and efficient paradigm to address data sparsity and cold-start issues in CDR, named CDR-Adapter, by decoupling the original recommendation model from the mapping function, without requiring re-engineering the network structure.

Recommendation Systems Transfer Learning

Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V

1 code implementation29 Oct 2023 Zhiling Yan, Kai Zhang, Rong Zhou, Lifang He, Xiang Li, Lichao Sun

In this paper, we critically evaluate the capabilities of the state-of-the-art multimodal large language model, i. e., GPT-4 with Vision (GPT-4V), on Visual Question Answering (VQA) task.

Language Modelling Large Language Model +2

FERI: A Multitask-based Fairness Achieving Algorithm with Applications to Fair Organ Transplantation

no code implementations20 Oct 2023 Can Li, Dejian Lai, Xiaoqian Jiang, Kai Zhang

Liver transplantation often faces fairness challenges across subgroups defined by sensitive attributes like age group, gender, and race/ethnicity.

Fairness

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking

1 code implementation NeurIPS 2023 Yang Yu, Qi Liu, Kai Zhang, Yuren Zhang, Chao Song, Min Hou, Yuqing Yuan, Zhihao Ye, Zaixi Zhang, Sanshi Lei Yu

Specifically, we adopt a multiple pairwise ranking loss which trains the user model to capture the similarity orders between the implicitly augmented view, the explicitly augmented view, and views from other users.

Contrastive Learning Data Augmentation

Multimodal Question Answering for Unified Information Extraction

1 code implementation4 Oct 2023 Yuxuan Sun, Kai Zhang, Yu Su

In addition, the effectiveness of our framework can successfully transfer to the few-shot setting, enhancing LMMs on a scale of 10B parameters to be competitive or outperform much larger language models such as ChatGPT and GPT-4.

Question Answering

ImagenHub: Standardizing the evaluation of conditional image generation models

2 code implementations2 Oct 2023 Max Ku, Tianle Li, Kai Zhang, Yujie Lu, Xingyu Fu, Wenwen Zhuang, Wenhu Chen

Recently, a myriad of conditional image generation and editing models have been developed to serve different downstream tasks, including text-to-image generation, text-guided image editing, subject-driven image generation, control-guided image generation, etc.

Conditional Image Generation text-guided-image-editing

Subjective Face Transform using Human First Impressions

1 code implementation27 Sep 2023 Chaitanya Roygaga, Joshua Krinsky, Kai Zhang, Kenny Kwok, Aparna Bharati

Humans tend to form quick subjective first impressions of non-physical attributes when seeing someone's face, such as perceived trustworthiness or attractiveness.

Attribute

Memory-Augmented LLM Personalization with Short- and Long-Term Memory Coordination

no code implementations21 Sep 2023 Kai Zhang, Fubang Zhao, Yangyang Kang, Xiaozhong Liu

However, we contend that a mere memory module is inadequate to comprehend a user's preference, and fully training an LLM can be excessively costly.

Designs and Implementations in Neural Network-based Video Coding

no code implementations11 Sep 2023 Yue Li, Junru Li, Chaoyi Lin, Kai Zhang, Li Zhang, Franck Galpin, Thierry Dumas, Hongtao Wang, Muhammed Coban, Jacob Ström, Du Liu, Kenneth Andersson

The past decade has witnessed the huge success of deep learning in well-known artificial intelligence applications such as face recognition, autonomous driving, and large language model like ChatGPT.

Autonomous Driving Face Recognition +3

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

1 code implementation NeurIPS 2023 Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, Yu Su

To address this issue, we introduce MagicBrush (https://osu-nlp-group. github. io/MagicBrush/), the first large-scale, manually annotated dataset for instruction-guided real image editing that covers diverse scenarios: single-turn, multi-turn, mask-provided, and mask-free editing.

text-guided-image-editing

A Feature Reuse Framework with Texture-adaptive Aggregation for Reference-based Super-Resolution

1 code implementation2 Jun 2023 Xiaoyong Mei, Yi Yang, Ming Li, Changqin Huang, Kai Zhang, Pietro Lió

In this study, we propose a feature reuse framework that guides the step-by-step texture reconstruction process through different stages, reducing the negative impacts of perceptual and adversarial loss.

Image Super-Resolution Reference-based Super-Resolution

Decomposed Human Motion Prior for Video Pose Estimation via Adversarial Training

no code implementations30 May 2023 Wenshuo Chen, Xiang Zhou, Zhengdi Yu, Weixi Gu, Kai Zhang

Estimating human pose from video is a task that receives considerable attention due to its applicability in numerous 3D fields.

Ranked #59 on 3D Human Pose Estimation on 3DPW (PA-MPJPE metric)

3D Human Pose Estimation

PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology

1 code implementation24 May 2023 Yuxuan Sun, Chenglu Zhu, Sunyi Zheng, Kai Zhang, Lin Sun, Zhongyi Shui, Yunlong Zhang, Honglin Li, Lin Yang

Secondly, by leveraging the collected data, we construct PathCLIP, a pathology-dedicated CLIP, to enhance PathAsst's capabilities in interpreting pathology images.

Instruction Following Language Modelling +1

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

1 code implementation22 May 2023 Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, Yu Su

By providing external information to large language models (LLMs), tool augmentation (including retrieval augmentation) has emerged as a promising solution for addressing the limitations of LLMs' static parametric memory.

Retrieval

Equivariant Multi-Modality Image Fusion

2 code implementations19 May 2023 Zixiang Zhao, Haowen Bai, Jiangshe Zhang, Yulun Zhang, Kai Zhang, Shuang Xu, Dongdong Chen, Radu Timofte, Luc van Gool

Multi-modality image fusion is a technique used to combine information from different sensors or modalities, allowing the fused image to retain complementary features from each modality, such as functional highlights and texture details.

Self-Supervised Learning

Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors

1 code implementation18 May 2023 Kai Zhang, Bernal Jiménez Gutiérrez, Yu Su

Recent work has shown that fine-tuning large language models (LLMs) on large-scale instruction-following datasets substantially improves their performance on a wide range of NLP tasks, especially in the zero-shot setting.

Instruction Following Question Answering +2

Denoising Diffusion Models for Plug-and-Play Image Restoration

2 code implementations15 May 2023 Yuanzhi Zhu, Kai Zhang, Jingyun Liang, JieZhang Cao, Bihan Wen, Radu Timofte, Luc van Gool

Although diffusion models have shown impressive performance for high-quality image synthesis, their potential to serve as a generative denoiser prior to the plug-and-play IR methods remains to be further explored.

Deblurring Denoising +4

Automatic Evaluation of Attribution by Large Language Models

1 code implementation10 May 2023 Xiang Yue, Boshi Wang, Ziru Chen, Kai Zhang, Yu Su, Huan Sun

We manually curate a set of test examples covering 12 domains from a generative search engine, New Bing.

Fact Checking Language Modelling +3

Sensitive Data Detection with High-Throughput Machine Learning Models in Electrical Health Records

no code implementations30 Apr 2023 Kai Zhang, Xiaoqian Jiang

Based on this novel finding, we engineered over 30 features from the metadata of the original features and used machine learning to build classification models to automatically identify PHI fields in structured Electronic Health Record (EHR) data.

De-identification

Ray Conditioning: Trading Photo-consistency for Photo-realism in Multi-view Image Generation

no code implementations ICCV 2023 Eric Ming Chen, Sidhanth Holalkere, Ruyu Yan, Kai Zhang, Abe Davis

Multi-view image generation attracts particular attention these days due to its promising 3D-related applications, e. g., image viewpoint editing.

Image Generation

A Scalable Test Problem Generator for Sequential Transfer Optimization

2 code implementations17 Apr 2023 Xiaoming Xue, Cuie Yang, Liang Feng, Kai Zhang, Linqi Song, Kay Chen Tan

Lastly, a benchmark suite with 12 STO problems featured by a variety of customized similarity relationships is developed using the proposed generator.

Predicting multiple sclerosis disease severity with multimodal deep neural networks

1 code implementation8 Apr 2023 Kai Zhang, John A. Lincoln, Xiaoqian Jiang, Elmer V. Bernstam, Shayan Shams

Multiple Sclerosis (MS) is a chronic disease developed in human brain and spinal cord, which can cause permanent damage or deterioration of the nerves.

Disease Prediction

ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge

1 code implementation24 Mar 2023 Yunxiang Li, Zihan Li, Kai Zhang, Ruilong Dan, Steve Jiang, You Zhang

The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a specialized language model with enhanced accuracy in medical advice.

Information Retrieval Language Modelling +3

A Comprehensive Survey on Instruction Following

1 code implementation18 Mar 2023 Renze Lou, Kai Zhang, Wenpeng Yin

This survey paper tries to summarize and provide insights to the current research on instruction following, particularly, by answering the following questions: (i) What is task instruction, and what instruction types exist?

Instruction Following

DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion

2 code implementations ICCV 2023 Zixiang Zhao, Haowen Bai, Yuanzhi Zhu, Jiangshe Zhang, Shuang Xu, Yulun Zhang, Kai Zhang, Deyu Meng, Radu Timofte, Luc van Gool

To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM).

Denoising

QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image Compression

6 code implementations10 Mar 2023 Kedeng Tong, Yaojun Wu, Yue Li, Kai Zhang, Li Zhang, Xin Jin

In this paper, we present a Quantization-error-aware Variable Rate Framework (QVRF) that utilizes a univariate quantization regulator a to achieve wide-range variable rates within a single model.

Image Compression Quantization

Memory-adaptive Depth-wise Heterogenous Federated Learning

1 code implementation8 Mar 2023 Kai Zhang, Yutong Dai, Hongyi Wang, Eric Xing, Xun Chen, Lichao Sun

Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data.

Federated Learning

Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation

no code implementations5 Mar 2023 Yixin Liu, Haohui Ye, Kai Zhang, Lichao Sun

The volume of open-source biomedical data has been essential to the development of various spheres of the healthcare community since more `free' data can provide individual researchers more chances to contribute.

Fairly Predicting Graft Failure in Liver Transplant for Organ Assigning

no code implementations18 Feb 2023 Sirui Ding, Ruixiang Tang, Daochen Zha, Na Zou, Kai Zhang, Xiaoqian Jiang, Xia Hu

To tackle this problem, this work proposes a fair machine learning framework targeting graft failure prediction in liver transplant.

Fairness Knowledge Distillation

A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT

no code implementations18 Feb 2023 Ce Zhou, Qian Li, Chen Li, Jun Yu, Yixin Liu, Guangjing Wang, Kai Zhang, Cheng Ji, Qiben Yan, Lifang He, Hao Peng, JianXin Li, Jia Wu, Ziwei Liu, Pengtao Xie, Caiming Xiong, Jian Pei, Philip S. Yu, Lichao Sun

This study provides a comprehensive review of recent research advancements, challenges, and opportunities for PFMs in text, image, graph, as well as other data modalities.

Graph Learning Language Modelling +1

Building Shortcuts between Distant Nodes with Biaffine Mapping for Graph Convolutional Networks

no code implementations17 Feb 2023 Acong Zhang, Jincheng Huang, Ping Li, Kai Zhang

Multiple recent studies show a paradox in graph convolutional networks (GCNs), that is, shallow architectures limit the capability of learning information from high-order neighbors, while deep architectures suffer from over-smoothing or over-squashing.

Contrastive Learning Node Classification +1

Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images

1 code implementation10 Dec 2022 Lei Ding, Jing Zhang, Kai Zhang, Haitao Guo, Bing Liu, Lorenzo Bruzzone

Semantic Change Detection (SCD) refers to the task of simultaneously extracting the changed areas and the semantic categories (before and after the changes) in Remote Sensing Images (RSIs).

Change Detection

GreenEyes: An Air Quality Evaluating Model based on WaveNet

1 code implementation8 Dec 2022 Kan Huang, Kai Zhang, Ming Liu

Accompanying rapid industrialization, humans are suffering from serious air pollution problems.

SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization

1 code implementation NIPS 2022 Zheng Chuanyang, Zheyang Li, Kai Zhang, Zhi Yang, Wenming Tan, Jun Xiao, Ye Ren, ShiLiang Pu

In this paper, we introduce joint importance, which integrates essential structural-aware interactions between components for the first time, to perform collaborative pruning.

object-detection Object Detection

Changes from Classical Statistics to Modern Statistics and Data Science

no code implementations30 Oct 2022 Kai Zhang, Shan Liu, Momiao Xiong

We urgently need to shift the paradigm for data analysis from the classical Euclidean data analysis to both Euclidean and non Euclidean data analysis and develop more and more innovative methods for describing, estimating and inferring non Euclidean geometries of modern real datasets.

BELIEF in Dependence: Leveraging Atomic Linearity in Data Bits for Rethinking Generalized Linear Models

no code implementations19 Oct 2022 Benjamin Brown, Kai Zhang, Xiao-Li Meng

Two linearly uncorrelated binary variables must be also independent because non-linear dependence cannot manifest with only two possible states.

LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval

1 code implementation29 Aug 2022 Kai Zhang, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, Binxing Jiao, Daxin Jiang

The alignment is achieved by weakened knowledge distillations to enlighten the retriever via two aspects -- 1) a lexicon-augmented contrastive objective to challenge the dense encoder and 2) a pair-wise rank-consistent regularization to make dense model's behavior incline to the other.

Representation Learning Retrieval

Hierarchical Reinforcement Learning Based Video Semantic Coding for Segmentation

no code implementations24 Aug 2022 Guangqi Xie, Xin Li, Shiqi Lin, Li Zhang, Kai Zhang, Yue Li, Zhibo Chen

In this paper, we take a step forward to video semantic compression and propose the Hierarchical Reinforcement Learning based task-driven Video Semantic Coding, named as HRLVSC.

Hierarchical Reinforcement Learning reinforcement-learning +3

Query-Response Interactions by Multi-tasks in Semantic Search for Chatbot Candidate Retrieval

no code implementations23 Aug 2022 Libin Shi, Kai Zhang, Wenge Rong

Semantic search for candidate retrieval is an important yet neglected problem in retrieval-based Chatbots, which aims to select a bunch of candidate responses efficiently from a large pool.

Chatbot Retrieval

Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting

2 code implementations5 Aug 2022 Juyong Jiang, Binqing Wu, Ling Chen, Kai Zhang, Sunghun Kim

On the one hand, our model simultaneously incorporates spatial (node-wise) embeddings and temporal (time-wise) embeddings to account for heterogeneous space-and-time convolutions; on the other hand, it uses GAN structure to systematically evaluate statistical consistencies between the real and the predicted time series in terms of both the temporal trending and the complex spatial-temporal dependencies.

Time Series Time Series Analysis

Unified Normalization for Accelerating and Stabilizing Transformers

1 code implementation2 Aug 2022 Qiming Yang, Kai Zhang, Chaoxiang Lan, Zhi Yang, Zheyang Li, Wenming Tan, Jun Xiao, ShiLiang Pu

To tackle these issues, we propose Unified Normalization (UN), which can speed up the inference by being fused with other linear operations and achieve comparable performance on par with LN.

Towards Interpretable Video Super-Resolution via Alternating Optimization

1 code implementation21 Jul 2022 JieZhang Cao, Jingyun Liang, Kai Zhang, Wenguan Wang, Qin Wang, Yulun Zhang, Hao Tang, Luc van Gool

These issues can be alleviated by a cascade of three separate sub-tasks, including video deblurring, frame interpolation, and super-resolution, which, however, would fail to capture the spatial and temporal correlations among video sequences.

Deblurring Space-time Video Super-resolution +2

Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss

1 code implementation21 Jun 2022 Yikang Ding, Zhenyang Li, Dihe Huang, Zhiheng Li, Kai Zhang

Learning-based multi-view stereo (MVS) methods have made impressive progress and surpassed traditional methods in recent years.

Contrastive Learning

ARF: Artistic Radiance Fields

1 code implementation13 Jun 2022 Kai Zhang, Nick Kolkin, Sai Bi, Fujun Luan, Zexiang Xu, Eli Shechtman, Noah Snavely

We present a method for transferring the artistic features of an arbitrary style image to a 3D scene.

MORE: A Metric Learning Based Framework for Open-domain Relation Extraction

1 code implementation1 Jun 2022 Yutong Wang, Renze Lou, Kai Zhang, MaoYan Chen, Yujiu Yang

To address these problems, in this work, we propose a novel learning framework named MORE (Metric learning-based Open Relation Extraction).

Clustering Metric Learning +2

WT-MVSNet: Window-based Transformers for Multi-view Stereo

no code implementations28 May 2022 Jinli Liao, Yikang Ding, Yoli Shavit, Dihe Huang, Shihao Ren, Jia Guo, Wensen Feng, Kai Zhang

In this work, we propose Window-based Transformers (WT) for local feature matching and global feature aggregation in multi-view stereo.

Graph Adaptive Semantic Transfer for Cross-domain Sentiment Classification

no code implementations18 May 2022 Kai Zhang, Qi Liu, Zhenya Huang, Mingyue Cheng, Kun Zhang, Mengdi Zhang, Wei Wu, Enhong Chen

Existing studies in this task attach more attention to the sequence modeling of sentences while largely ignoring the rich domain-invariant semantics embedded in graph structures (i. e., the part-of-speech tags and dependency relations).

Classification Graph Attention +4

NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results

2 code implementations11 May 2022 Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang

The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.

Image Super-Resolution

Adversarial Learning of Hard Positives for Place Recognition

no code implementations8 May 2022 Wenxuan Fang, Kai Zhang, Yoli Shavit, Wensen Feng

Our method learns local and global augmentation policies which will increase the training loss, while the image retrieval network is forced to learn more powerful features for discriminating increasingly difficult examples.

Image Retrieval Retrieval

Discussion of Multiscale Fisher's Independence Test for Multivariate Dependence

no code implementations26 Apr 2022 Duyeol Lee, Helal El-Zaatari, Michael R. Kosorok, Xinyi Li, Kai Zhang

In this comment, we would like to discuss a general framework unifying the MULTIFIT and other tests and compare it with the binary expansion randomized ensemble test (BERET hereafter) proposed by Lee et al. (In press).

Indoor simultaneous localization and mapping based on fringe projection profilometry

no code implementations23 Apr 2022 Yang Zhao, Kai Zhang, Haotian Yu, Yi Zhang, Dongliang Zheng, Jing Han

Simultaneous Localization and Mapping (SLAM) plays an important role in outdoor and indoor applications ranging from autonomous driving to indoor robotics.

Autonomous Driving Simultaneous Localization and Mapping

IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images

no code implementations CVPR 2022 Kai Zhang, Fujun Luan, Zhengqi Li, Noah Snavely

We propose a neural inverse rendering pipeline called IRON that operates on photometric images and outputs high-quality 3D content in the format of triangle meshes and material textures readily deployable in existing graphics pipelines.

Disentanglement Inverse Rendering

APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction

1 code implementation30 Mar 2022 Bencheng Yan, Pengjie Wang, Kai Zhang, Feng Li, Hongbo Deng, Jian Xu, Bo Zheng

In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted.

Click-Through Rate Prediction

Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis

2 code implementations24 Mar 2022 Kai Zhang, Yawei Li, Jingyun Liang, JieZhang Cao, Yulun Zhang, Hao Tang, Deng-Ping Fan, Radu Timofte, Luc van Gool

While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved.

Image Denoising Image-to-Image Translation

Phased Flight Trajectory Prediction with Deep Learning

no code implementations17 Mar 2022 Kai Zhang, Bowen Chen

The unprecedented increase of commercial airlines and private jets over the next ten years presents a challenge for air traffic control.

Decision Making Management +1

Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation

1 code implementation17 Mar 2022 Kai Zhang, Yu Wang, Hongyi Wang, Lifu Huang, Carl Yang, Xun Chen, Lichao Sun

Furthermore, we propose a Federated learning paradigm with privacy-preserving Relation embedding aggregation (FedR) to tackle the privacy issue in FedE.

Entity Embeddings Federated Learning +4

Self-supervised Transparent Liquid Segmentation for Robotic Pouring

1 code implementation3 Mar 2022 Gautham Narayan Narasimhan, Kai Zhang, Ben Eisner, Xingyu Lin, David Held

Liquid state estimation is important for robotics tasks such as pouring; however, estimating the state of transparent liquids is a challenging problem.

Segmentation

VRT: A Video Restoration Transformer

1 code implementation28 Jan 2022 Jingyun Liang, JieZhang Cao, Yuchen Fan, Kai Zhang, Rakesh Ranjan, Yawei Li, Radu Timofte, Luc van Gool

Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping.

Deblurring Denoising +7

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.

feature selection

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

Sequential Recommendation with Bidirectional Chronological Augmentation of Transformer

no code implementations13 Dec 2021 Juyong Jiang, Yingtao Luo, Jae Boum Kim, Kai Zhang, Sunghun Kim

Sequential recommendation can capture user chronological preferences from their historical behaviors, yet the learning of short sequences (cold-start problem) in many benchmark datasets is still an open challenge.

Data Augmentation Self-Knowledge Distillation +1

Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation

1 code implementation1 Dec 2021 Kai Zhang, Yifan Sun, Rui Wang, Haichang Li, Xiaohui Hu

MFA basically considers three parallel information fusion strategies, i. e., the cross-model fusion, temporal fusion and a novel online-offline pseudo label fusion.

Pseudo Label Segmentation +3

Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine

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

Causal structure learning refers to a process of identifying causal structures from observational data, and it can have multiple applications in biomedicine and health care.

BIG-bench Machine Learning Causal Discovery +1

Towards Flexible Blind JPEG Artifacts Removal

2 code implementations 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

9 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 Grayscale Image Denoising +6

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

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

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 +2

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.

XLM-R

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.

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.

Clustering Relation +1

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.

Depth Prediction Image Relighting +3

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

3 code implementations 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 Video 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 Management +1

Local Change Point Detection and Cleaning of EEMD Signals with Application 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

BEAUTY Powered BEAST

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

To approach this oracle power, we devise the BEAST through a regularized resampling approximation of the oracle test.

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

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

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

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

5 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.

Classification Document Classification +2

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

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

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

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 Sentence

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.

Sentence

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.

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

3 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.

Computational Efficiency Image Denoising +2

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

6 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.

Color Image Denoising Image Denoising

Learning Deep CNN Denoiser Prior for Image Restoration

2 code implementations 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

20 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.

Color Image Denoising Image Deblocking +3

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.

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.