Search Results for author: Kai Li

Found 62 papers, 25 papers with code

Instance-hiding Schemes for Private Distributed Learning

no code implementations ICML 2020 Yangsibo Huang, Zhao Song, Sanjeev Arora, Kai Li

The new ideas in the current paper are: (a) new variants of mixup with negative as well as positive coefficients, and extend the sample-wise mixup to be pixel-wise.

Federated Learning

Designs, Motion Mechanism, Motion Coordination, and Communication of Bionic Robot Fishes: A Survey

no code implementations30 Jun 2022 Zhiwei Yu, Kai Li, Yu Ji, Simon X. Yang

Various methods are needed to narrow the gap in swimming performance between robot fishes and fish.

Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications

1 code implementation22 May 2022 Fanglei Sun, Yang Li, Ying Wen, Jingchen Hu, Jun Wang, Yang Yang, Kai Li

The design of MAFENN framework and algorithm are dedicated to enhance the learning capability of the feedfoward DL networks or their variations with the simple data feedback.


Recovering Private Text in Federated Learning of Language Models

1 code implementation17 May 2022 Samyak Gupta, Yangsibo Huang, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen

In this paper, we present a novel attack method FILM for federated learning of language models -- for the first time, we show the feasibility of recovering text from large batch sizes of up to 128 sentences.

Federated Learning

Fast Few-shot Debugging for NLU Test Suites

1 code implementation DeeLIO (ACL) 2022 Christopher Malon, Kai Li, Erik Kruus

We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem.

Natural Language Understanding

Downlink Channel Covariance Matrix Reconstruction for FDD Massive MIMO Systems with Limited Feedback

no code implementations2 Apr 2022 Kai Li, Ying Li, Lei Cheng, Qingjiang Shi, Zhi-Quan Luo

The downlink channel covariance matrix (CCM) acquisition is the key step for the practical performance of massive multiple-input and multiple-output (MIMO) systems, including beamforming, channel tracking, and user scheduling.

StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis

1 code implementation CVPR 2022 Zhiheng Li, Martin Renqiang Min, Kai Li, Chenliang Xu

Based on the identified latent directions of attributes, we propose Compositional Attribute Adjustment to adjust the latent code, resulting in better compositionality of image synthesis.

Fairness Image Generation

Exploring Deep Reinforcement Learning-Assisted Federated Learning for Online Resource Allocation in Privacy-Persevering EdgeIoT

1 code implementation15 Feb 2022 Jingjing Zheng, Kai Li, Naram Mhaisen, Wei Ni, Eduardo Tovar, Mohsen Guizani

Federated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile edge computing-based Internet of Thing (EdgeIoT).

Edge-computing Federated Learning +1

Evaluating Gradient Inversion Attacks and Defenses in Federated Learning

1 code implementation NeurIPS 2021 Yangsibo Huang, Samyak Gupta, Zhao Song, Kai Li, Sanjeev Arora

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the clients' private data.

Federated Learning

Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game

no code implementations ICLR 2022 Haobo Fu, Weiming Liu, Shuang Wu, Yijia Wang, Tao Yang, Kai Li, Junliang Xing, Bin Li, Bo Ma, Qiang Fu, Yang Wei

The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.

Policy Gradient Methods

CarNet: A Lightweight and Efficient Encoder-Decoder Architecture for High-quality Road Crack Detection

no code implementations13 Sep 2021 Kai Li, Yingjie Tian, Zhiquan Qi

In this paper, we present a lightweight encoder-decoder architecture, CarNet, for efficient and high-quality crack detection.

EMA: Auditing Data Removal from Trained Models

1 code implementation8 Sep 2021 Yangsibo Huang, Xiaoxiao Li, Kai Li

In this paper, we propose a new method called Ensembled Membership Auditing (EMA) for auditing data removal to overcome these limitations.

Plot2Spectra: an Automatic Spectra Extraction Tool

1 code implementation6 Jul 2021 Weixin Jiang, Eric Schwenker, Trevor Spreadbury, Kai Li, Maria K. Y. Chan, Oliver Cossairt

In scientific literature, XANES/Raman data are usually plotted in line graphs which is a visually appropriate way to represent the information when the end-user is a human reader.

Optical Flow Estimation Semantic Segmentation

Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function

no code implementations29 Jun 2021 Kai Li, Bo wang, Yingjie Tian, Zhiquan Qi

Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance.

MR Image Super-Resolution With Squeeze and Excitation Reasoning Attention Network

no code implementations CVPR 2021 Yulun Zhang, Kai Li, Kunpeng Li, Yun Fu

They also fail to sense the entire space of the input, which is critical for high-quality MR image SR. To address those problems, we propose squeeze and excitation reasoning attention networks (SERAN) for accurate MR image SR. We propose to squeeze attention from global spatial information of the input and obtain global descriptors.

Image Super-Resolution

Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment

no code implementations1 Jun 2021 Tianze Zhou, Fubiao Zhang, Kun Shao, Kai Li, Wenhan Huang, Jun Luo, Weixun Wang, Yaodong Yang, Hangyu Mao, Bin Wang, Dong Li, Wulong Liu, Jianye Hao

In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.

Management Multi-agent Reinforcement Learning +3

Cooperative Multi-Agent Reinforcement Learning with Sequential Credit Assignment

1 code implementation NeurIPS 2021 Yifan Zang, Jinmin He, Kai Li, Lily Cao, Haobo Fu, Qiang Fu, Junliang Xing

In this paper, we propose a cooperative MARL method with sequential credit assignment (SeCA) that deduces each agent's contribution to the team's success one by one to learn better cooperation.

Multi-agent Reinforcement Learning reinforcement-learning +2

ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation

1 code implementation ICCV 2021 Kai Li, Chang Liu, Handong Zhao, Yulun Zhang, Yun Fu

This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain.

Data Augmentation Domain Adaptation

RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks

no code implementations18 Apr 2021 Kai Li, Curtis Wigington, Chris Tensmeyer, Vlad I. Morariu, Handong Zhao, Varun Manjunatha, Nikolaos Barmpalios, Yun Fu

Contrasted with prior work, this paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.

L2E: Learning to Exploit Your Opponent

no code implementations18 Feb 2021 Zhe Wu, Kai Li, Enmin Zhao, Hang Xu, Meng Zhang, Haobo Fu, Bo An, Junliang Xing

In this work, we propose a novel Learning to Exploit (L2E) framework for implicit opponent modeling.

VINS: Visual Search for Mobile User Interface Design

1 code implementation10 Feb 2021 Sara Bunian, Kai Li, Chaima Jemmali, Casper Harteveld, Yun Fu, Magy Seif El-Nasr

By utilizing this dataset, we propose an object-detection based image retrieval framework that models the UI context and hierarchical structure.

Image Retrieval object-detection +1

Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details

no code implementations20 Jan 2021 Zhuqing Jiang, Chang Liu, Ya'nan Wang, Kai Li, Aidong Men, Haiying Wang, Haiyong Luo

With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography.

Low-Light Image Enhancement

Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References

no code implementations4 Jan 2021 Ya'nan Wang, Zhuqing Jiang, Chang Liu, Kai Li, Aidong Men, Haiying Wang

This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference.

Low-Light Image Enhancement Style Transfer

Temperature Regret Matching for Imperfect-Information Games

no code implementations1 Jan 2021 Enmin Zhao, Kai Li, Junliang Xing

Regret matching (RM) plays a crucial role in CFR and its variants to approach Nash equilibrium.

Video Matting via Consistency-Regularized Graph Neural Networks

no code implementations ICCV 2021 Tiantian Wang, Sifei Liu, Yapeng Tian, Kai Li, Ming-Hsuan Yang

In this paper, we propose to enhance the temporal coherence by Consistency-Regularized Graph Neural Networks (CRGNN) with the aid of a synthesized video matting dataset.

Image Matting Optical Flow Estimation +1

Neighbor Class Consistency on Unsupervised Domain Adaptation

no code implementations1 Jan 2021 Chang Liu, Kai Li, Yun Fu

Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data in a target domain with labeled data from source domain available.

Image Classification Unsupervised Domain Adaptation

OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research

no code implementations11 Dec 2020 Kai Li, Hang Xu, Enmin Zhao, Zhe Wu, Junliang Xing

Owning to the unremitting efforts by a few institutes, significant progress has recently been made in designing superhuman AIs in No-limit Texas Hold'em (NLTH), the primary testbed for large-scale imperfect-information game research.

DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio

no code implementations12 Nov 2020 Jiangtao Kong, Yu Cheng, Benjia Zhou, Kai Li, Junliang Xing

To obtain a high-performance vehicle ReID model, we present a novel Distance Shrinking with Angular Marginalizing (DSAM) loss function to perform hybrid learning in both the Original Feature Space (OFS) and the Feature Angular Space (FAS) using the local verification and the global identification information.

Person Re-Identification Vehicle Re-Identification

Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization

no code implementations23 Oct 2020 Li Ren, Kai Li, Liqiang Wang, Kien Hua

In this paper, we address this limitation with an efficient learning objective that considers the discriminative feature distributions between the visual objects and sentence words.

Metric Learning Natural Language Processing

Pushing The Limit of Type I Codebook For FDD Massive MIMO Beamforming: A Channel Covariance Reconstruction Approach

no code implementations22 Oct 2020 Kai Li, Ying Li, Lei Cheng, Qingjiang Shi, Zhi-Quan Luo

There is a fundamental trade-off between the channel representation resolution of codebooks and the overheads of feedback communications in the fifth generation new radio (5G NR) frequency division duplex (FDD) massive multiple-input and multiple-output (MIMO) systems.

MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery

no code implementations22 Oct 2020 Xiaoxiao Li, Yangsibo Huang, Binghui Peng, Zhao Song, Kai Li

To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data representations, as a way to control the trade-off between data utility and vulnerability to inversion attacks.

InstaHide: Instance-hiding Schemes for Private Distributed Learning

3 code implementations6 Oct 2020 Yangsibo Huang, Zhao Song, Kai Li, Sanjeev Arora

This paper introduces InstaHide, a simple encryption of training images, which can be plugged into existing distributed deep learning pipelines.

Light Field View Synthesis via Aperture Disparity and Warping Confidence Map

no code implementations7 Sep 2020 Nan Meng, Kai Li, Jianzhuang Liu, Edmund Y. Lam

This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images.

Novel View Synthesis

Cross-Domain Document Object Detection: Benchmark Suite and Method

1 code implementation CVPR 2020 Kai Li, Curtis Wigington, Chris Tensmeyer, Handong Zhao, Nikolaos Barmpalios, Vlad I. Morariu, Varun Manjunatha, Tong Sun, Yun Fu

We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation.

object-detection Object Detection

Adversarial Feature Hallucination Networks for Few-Shot Learning

no code implementations CVPR 2020 Kai Li, Yulun Zhang, Kunpeng Li, Yun Fu

The recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data.

Data Augmentation Few-Shot Learning

Privacy-preserving Learning via Deep Net Pruning

no code implementations4 Mar 2020 Yangsibo Huang, Yushan Su, Sachin Ravi, Zhao Song, Sanjeev Arora, Kai Li

This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility.

Network Pruning Privacy Preserving

Learning Relaxed Belady for Content Distribution Network Caching

1 code implementation25 Feb 2020 Zhenyu Song, Daniel S. Berger, Kai Li, Wyatt Lloyd

This paper presents a new approach for caching in CDNs that uses machine learning to approximate the Belady MIN algorithm.

BIG-bench Machine Learning

Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

1 code implementation ICCV 2019 Kai Li, Martin Renqiang Min, Yun Fu

We instead reformulate ZSL as a conditioned visual classification problem, i. e., classifying visual features based on the classifiers learned from the semantic descriptions.

Classification General Classification +1

Visual Semantic Reasoning for Image-Text Matching

1 code implementation ICCV 2019 Kunpeng Li, Yulun Zhang, Kai Li, Yuanyuan Li, Yun Fu

It outperforms the current best method by 6. 8% relatively for image retrieval and 4. 8% relatively for caption retrieval on MS-COCO (Recall@1 using 1K test set).

Cross-Modal Retrieval Image Retrieval +1

On-board Deep Q-Network for UAV-assisted Online Power Transfer and Data Collection

no code implementations4 Jun 2019 Kai Li, Wei Ni, Eduardo Tovar

A key challenge is online MPT and data collection in the presence of on-board control of a UAV (e. g., patrolling velocity) for preventing battery drainage and data queue overflow of the sensing devices, while up-to-date knowledge on battery level and data queue of the devices is not available at the UAV.

Q-Learning reinforcement-learning

Authenticated Key-Value Stores with Hardware Enclaves

no code implementations26 Apr 2019 Yuzhe Tang, Ju Chen, Kai Li, Jianliang Xu, Qi Zhang

To circumvent the limited enclave memory (128 MB with the latest Intel CPUs), we propose to place the memory buffer of the eLSM store outside the enclave and protect the buffer using a new authenticated data structure by digesting individual LSM-tree levels.

Cryptography and Security Databases Distributed, Parallel, and Cluster Computing Data Structures and Algorithms

Residual Non-local Attention Networks for Image Restoration

2 code implementations ICLR 2019 Yulun Zhang, Kunpeng Li, Kai Li, Bineng Zhong, Yun Fu

To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts.

Demosaicking Image Denoising +1

PZnet: Efficient 3D ConvNet Inference on Manycore CPUs

no code implementations18 Mar 2019 Sergiy Popovych, Davit Buniatyan, Aleksandar Zlateski, Kai Li, H. Sebastian Seung

Convolutional nets have been shown to achieve state-of-the-art accuracy in many biomedical image analysis tasks.

Fast 3D Line Segment Detection From Unorganized Point Cloud

3 code implementations8 Jan 2019 Xiaohu Lu, Yahui Liu, Kai Li

This paper presents a very simple but efficient algorithm for 3D line segment detection from large scale unorganized point cloud.

Line Detection Line Segment Detection +1

Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction

no code implementations5 Dec 2018 Ken Chen, Fei Chen, Baisheng Lai, Zhongming Jin, Yong liu, Kai Li, Long Wei, Pengfei Wang, Yandong Tang, Jianqiang Huang, Xian-Sheng Hua

To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream.

Traffic Prediction

Support Neighbor Loss for Person Re-Identification

1 code implementation18 Aug 2018 Kai Li, Zhengming Ding, Kunpeng Li, Yulun Zhang, Yun Fu

To ensure scalability and separability, a softmax-like function is formulated to push apart the positive and negative support sets.

Person Re-Identification

Payoff Control in the Iterated Prisoner's Dilemma

no code implementations17 Jul 2018 Dong Hao, Kai Li, Tao Zhou

Repeated game has long been the touchstone model for agents' long-run relationships.

Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation

no code implementations CVPR 2018 Kai Li, Junliang Xing, Chi Su, Weiming Hu, Yundong Zhang, Stephen Maybank

First, a novel cost-sensitive multi-task loss function is designed to learn transferable aging features by training on the source population.

Age Estimation

Deep Ordinal Hashing with Spatial Attention

no code implementations7 May 2018 Lu Jin, Xiangbo Shu, Kai Li, Zechao Li, Guo-Jun Qi, Jinhui Tang

However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images.

Image Retrieval

Large Linear Multi-output Gaussian Process Learning

1 code implementation30 May 2017 Vladimir Feinberg, Li-Fang Cheng, Kai Li, Barbara E. Engelhardt

Gaussian processes (GPs), or distributions over arbitrary functions in a continuous domain, can be generalized to the multi-output case: a linear model of coregionalization (LMC) is one approach.

Gaussian Processes Time Series

Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction

1 code implementation27 Mar 2017 Li-Fang Cheng, Gregory Darnell, Bianca Dumitrascu, Corey Chivers, Michael E Draugelis, Kai Li, Barbara E. Engelhardt

In the scenario of real-time monitoring of hospital patients, high-quality inference of patients' health status using all information available from clinical covariates and lab tests is essential to enable successful medical interventions and improve patient outcomes.

Gaussian Processes Time Series Prediction

Quantum cluster approach to the topological invariants in correlated Chern insulators

no code implementations16 Dec 2015 Zhao-Long Gu, Kai Li, Jian-Xin Li

We detect the topological properties of Chern insulators with strong Coulomb interactions by use of cluster perturbation theory and variational cluster approach.

Strongly Correlated Electrons

From rules to runs: A dynamic epistemic take on imperfect information games

no code implementations7 Dec 2015 Kai Li, Yanjing Wang

We argue that the problem lies in the mix-up of two interpretations of the extensive form game structures: game rules or game runs which do not always coincide.

First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos

no code implementations6 Jun 2015 Jun Ye, Hao Hu, Kai Li, Guo-Jun Qi, Kien A. Hua

With the prevalence of the commodity depth cameras, the new paradigm of user interfaces based on 3D motion capturing and recognition have dramatically changed the way of interactions between human and computers.

3D Action Recognition

Line-Based Multi-Label Energy Optimization for Fisheye Image Rectification and Calibration

no code implementations CVPR 2015 Mi Zhang, Jian Yao, Menghan Xia, Kai Li, Yi Zhang, Yaping Liu

Fisheye image rectification and estimation of intrinsic parameters for real scenes have been addressed in the literature by using line information on the distorted images.

Rank Subspace Learning for Compact Hash Codes

no code implementations19 Mar 2015 Kai Li, Guo-Jun Qi, Jun Ye, Kien A. Hua

In this work, we propose a novel hash learning framework that encodes feature's rank orders instead of numeric values in a number of optimal low-dimensional ranking subspaces.

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