Search Results for author: Yi Li

Found 187 papers, 56 papers with code

EgoPrivacy: What Your First-Person Camera Says About You?

no code implementations13 Jun 2025 Yijiang Li, Genpei Zhang, Jiacheng Cheng, Yi Li, Xiaojun Shan, Dashan Gao, Jiancheng Lyu, Yuan Li, Ning Bi, Nuno Vasconcelos

While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer.

The Invariant Zonotopic Set-Membership Filter for State Estimation on Groups

no code implementations10 Jun 2025 Tao Li, Yi Li, Lulin Zhang, Jiuxiang Dong

In this paper, considering the problem of state estimation with unknown but bounded noise disturbances, an Invariant Zonotopic Set-Membership Filter (InZSMF) method on groups is innovatively proposed, which extends the invariant filtering theory to the field of non-statistical filtering represented by set-membership filtering.

State Estimation

SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networks

no code implementations6 Jun 2025 Long Dang, Thushari Hapuarachchi, Kaiqi Xiong, Yi Li

In an in-vehicle network, these ECUs communicate with one another using an standard protocol called Controller Area Network (CAN).

UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation

no code implementations15 May 2025 Yi Li, Haonan Wang, Qixiang Zhang, Boyu Xiao, Chenchang Hu, Hualiang Wang, Xiaomeng Li

However, there is a lack of a unified evaluation framework for these models, which would enable an elegant, simplified, and overall evaluation.

Diversity Instruction Following

Leveraging Segment Anything Model for Source-Free Domain Adaptation via Dual Feature Guided Auto-Prompting

2 code implementations13 May 2025 Zheang Huai, Hui Tang, Yi Li, Zhuangzhuang Chen, Xiaomeng Li

Source-free domain adaptation (SFDA) for segmentation aims at adapting a model trained in the source domain to perform well in the target domain with only the source model and unlabeled target data. Inspired by the recent success of Segment Anything Model (SAM) which exhibits the generality of segmenting images of various modalities and in different domains given human-annotated prompts like bounding boxes or points, we for the first time explore the potentials of Segment Anything Model for SFDA via automatedly finding an accurate bounding box prompt.

Source-Free Domain Adaptation

Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network

1 code implementation11 May 2025 Fei Zhou, Yi Li, Mingqing Zhu

In this paper, the dual-optical attention fusion crowd head point counting model (TAPNet) is proposed to address the problem of the difficulty of accurate counting in complex scenes such as crowd dense occlusion and low light in crowd counting tasks under UAV view.

Crowd Counting Data Augmentation

TS-Diff: Two-Stage Diffusion Model for Low-Light RAW Image Enhancement

1 code implementation7 May 2025 Yi Li, Zhiyuan Zhang, Jiangnan Xia, Jianghan Cheng, Qilong Wu, Junwei Li, Yibin Tian, Hui Kong

During the aligning stage, CFIs are averaged to create a target-specific CFI$^T$, which is fine-tuned using a small amount of real RAW data to adapt to the noise characteristics of specific cameras.

Denoising Image Enhancement

Inferring Outcome Means of Exponential Family Distributions Estimated by Deep Neural Networks

no code implementations12 Apr 2025 Xuran Meng, Yi Li

While deep neural networks (DNNs) are widely used for prediction, inference on DNN-estimated subject-specific means for categorical or exponential family outcomes remains underexplored.

regression

Prototype-Based Continual Learning with Label-free Replay Buffer and Cluster Preservation Loss

no code implementations9 Apr 2025 Agil Aghasanli, Yi Li, Plamen Angelov

These mechanisms ensure the retention of previously learned information as well as adaptation to new classes or domain shifts.

Continual Learning

Intelligent Bear Prevention System Based on Computer Vision: An Approach to Reduce Human-Bear Conflicts in the Tibetan Plateau Area, China

no code implementations29 Mar 2025 PengYu Chen, Teng Fei, Yunyan Du, Jiawei Yi, Yi Li, John A. Kupfer

Conflicts between humans and bears on the Tibetan Plateau present substantial threats to local communities and hinder wildlife preservation initiatives.

object-detection Object Detection

Sparse Meets Dense: Unified Generative Recommendations with Cascaded Sparse-Dense Representations

no code implementations4 Mar 2025 Yuhao Yang, Zhi Ji, Zhaopeng Li, Yi Li, Zhonglin Mo, Yue Ding, Kai Chen, Zijian Zhang, Jie Li, Shuanglong Li, Lin Liu

To address this, we introduce the Cascaded Organized Bi-Represented generAtive retrieval (COBRA) framework, which innovatively integrates sparse semantic IDs and dense vectors through a cascading process.

Quantization Recommendation Systems +1

Split Adaptation for Pre-trained Vision Transformers

no code implementations CVPR 2025 Lixu Wang, Bingqi Shang, Yi Li, Payal Mohapatra, Wei Dong, Xiao Wang, Qi Zhu

SA, inspired by split learning (SL), segments the pre-trained ViT into a frontend and a backend, with only the frontend shared with the client for data representation extraction.

Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions

no code implementations1 Mar 2025 Guanwen Xie, Jingzehua Xu, Yimian Ding, Zhi Zhang, Shuai Zhang, Yi Li

The adaptivity and maneuvering capabilities of Autonomous Underwater Vehicles (AUVs) have drawn significant attention in oceanic research, due to the unpredictable disturbances and strong coupling among the AUV's degrees of freedom.

Language Modeling Language Modelling +2

Near-optimal Active Regression of Single-Index Models

no code implementations25 Feb 2025 Yi Li, Wai Ming Tai

The active regression problem of the single-index model is to solve $\min_x \lVert f(Ax)-b\rVert_p$, where $A$ is fully accessible and $b$ can only be accessed via entry queries, with the goal of minimizing the number of queries to the entries of $b$.

regression

Towards Secure Program Partitioning for Smart Contracts with LLM's In-Context Learning

no code implementations20 Feb 2025 Ye Liu, Yuqing Niu, Chengyan Ma, Ruidong Han, Wei Ma, Yi Li, Debin Gao, David Lo

Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information.

In-Context Learning

DeFiScope: Detecting Various DeFi Price Manipulations with LLM Reasoning

no code implementations17 Feb 2025 Juantao Zhong, Daoyuan Wu, Ye Liu, Maoyi Xie, Yang Liu, Yi Li, Ning Liu

DeFi (Decentralized Finance) is one of the most important applications of today's cryptocurrencies and smart contracts.

HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation

no code implementations8 Feb 2025 Yi Li, Yuquan Deng, Jesse Zhang, Joel Jang, Marius Memmel, Raymond Yu, Caelan Reed Garrett, Fabio Ramos, Dieter Fox, Anqi Li, Abhishek Gupta, Ankit Goyal

Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics.

Robot Manipulation Vision-Language-Action

Consensus statement on the credibility assessment of ML predictors

no code implementations30 Jan 2025 Alessandra Aldieri, Thiranja Prasad Babarenda Gamage, Antonino Amedeo La Mattina, Yi Li, Axel Loewe, Francesco Pappalardo, Marco Viceconti Italy

The rapid integration of machine learning (ML) predictors into in silico medicine has revolutionized the estimation of quantities of interest (QIs) that are otherwise challenging to measure directly.

Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks

no code implementations15 Jan 2025 Shuang Cui, Yi Li, Jiangmeng Li, Xiongxin Tang, Bing Su, Fanjiang Xu, Hui Xiong

Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains.

Deblurring Image Defocus Deblurring +1

Efficiently Serving Large Multimodal Models Using EPD Disaggregation

1 code implementation25 Dec 2024 Gursimran Singh, Xinglu Wang, Yifan Hu, Timothy Yu, Linzi Xing, Wei Jiang, Zhefeng Wang, Xiaolong Bai, Yi Li, Ying Xiong, Yong Zhang, Zhenan Fan

Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead.

Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation

no code implementations30 Nov 2024 Chengyu Li, Debo Cheng, Guixian Zhang, Yi Li, Shichao Zhang

To enhance information transfer, we incorporate graph-level distillation to provide an indirect supplement of graph information during training, as well as a node-specific temperature module to improve the comprehensive transfer of fair knowledge.

Fairness Graph Representation Learning +1

Dynamic Attention and Bi-directional Fusion for Safety Helmet Wearing Detection

no code implementations28 Nov 2024 Junwei Feng, Xueyan Fan, Yuyang Chen, Yi Li

Ensuring construction site safety requires accurate and real-time detection of workers' safety helmet use, despite challenges posed by cluttered environments, densely populated work areas, and hard-to-detect small or overlapping objects caused by building obstructions.

object-detection Small Object Detection

GRAPE: Generalizing Robot Policy via Preference Alignment

no code implementations28 Nov 2024 Zijian Zhang, Kaiyuan Zheng, Zhaorun Chen, Joel Jang, Yi Li, Siwei Han, Chaoqi Wang, Mingyu Ding, Dieter Fox, Huaxiu Yao

Notably, these constraints are flexible and can be customized to align the model with varying objectives, such as safety, efficiency, or task success.

Vision-Language-Action

Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum

no code implementations26 Nov 2024 Jing-Yang Wei, Hao Huang, Xin Zhang, De-Mao Ye, Yi Li, Le Wang, Yao-Guang Ma, Yang-Hui Li

To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system.

Generative Adversarial Network

YOSO: You-Only-Sample-Once via Compressed Sensing for Graph Neural Network Training

no code implementations8 Nov 2024 Yi Li, Zhichun Guo, Guanpeng Li, Bingzhe Li

Graph neural networks (GNNs) have become essential tools for analyzing non-Euclidean data across various domains.

compressed sensing Graph Neural Network +3

Multi-Objective-Optimization Multi-AUV Assisted Data Collection Framework for IoUT Based on Offline Reinforcement Learning

no code implementations15 Oct 2024 Yimian Ding, Xinqi Wang, Jingzehua Xu, Guanwen Xie, Weiyi Liu, Yi Li

To address these issues and the constraints of turbulent ocean environments, we propose a multi-AUV assisted data collection framework for IoUT based on multi-agent offline RL.

Collision Avoidance Offline RL +2

OptiGrasp: Optimized Grasp Pose Detection Using RGB Images for Warehouse Picking Robots

no code implementations29 Sep 2024 Soofiyan Atar, Yi Li, Markus Grotz, Michael Wolf, Dieter Fox, Joshua Smith

In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects.

ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models

1 code implementation21 Sep 2024 Yuqing Huang, Rongyang Zhang, Xuesong He, Xuyang Zhi, Hao Wang, Xin Li, Feiyang Xu, Deguang Liu, Huadong Liang, Yi Li, Jian Cui, Zimu Liu, Shijin Wang, Guoping Hu, Guiquan Liu, Qi Liu, Defu Lian, Enhong Chen

To this end, we propose \textbf{\textit{ChemEval}}, which provides a comprehensive assessment of the capabilities of LLMs across a wide range of chemical domain tasks.

Few-Shot Learning Instruction Following

SX-Stitch: An Efficient VMS-UNet Based Framework for Intraoperative Scoliosis X-Ray Image Stitching

no code implementations9 Sep 2024 Yi Li, Heting Gao, Mingde He, Jinqian Liang, Jason Gu, Wei Liu

In scoliosis surgery, the limited field of view of the C-arm X-ray machine restricts the surgeons' holistic analysis of spinal structures . This paper presents an end-to-end efficient and robust intraoperative X-ray image stitching method for scoliosis surgery, named SX-Stitch.

Image Segmentation Image Stitching +4

Community-Centric Graph Unlearning

no code implementations19 Aug 2024 Yi Li, Shichao Zhang, Guixian Zhang, Debo Cheng

Graph unlearning technology has become increasingly important since the advent of the `right to be forgotten' and the growing concerns about the privacy and security of artificial intelligence.

Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms

no code implementations16 Aug 2024 Yi Li, Honghao Lin, David P. Woodruff

Our algorithm can be extended to the $\ell_p$ sparse recovery problem with the same sketching dimension, which seems to be the first such bound for $p > 2$.

Fairness and Bias Mitigation in Computer Vision: A Survey

no code implementations5 Aug 2024 Sepehr Dehdashtian, Ruozhen He, Yi Li, Guha Balakrishnan, Nuno Vasconcelos, Vicente Ordonez, Vishnu Naresh Boddeti

Computer vision systems have witnessed rapid progress over the past two decades due to multiple advances in the field.

Fairness Survey

U-learning for Prediction Inference via Combinatory Multi-Subsampling: With Applications to LASSO and Neural Networks

no code implementations22 Jul 2024 Zhe Fei, Yi Li

Epigenetic aging clocks play a pivotal role in estimating an individual's biological age through the examination of DNA methylation patterns at numerous CpG (Cytosine-phosphate-Guanine) sites within their genome.

valid

Self-Supervised Representation Learning for Adversarial Attack Detection

no code implementations5 Jul 2024 Yi Li, Plamen Angelov, Neeraj Suri

Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.

Adversarial Attack Detection Representation Learning

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification

no code implementations24 Jun 2024 Alvaro Lopez Pellicer, Kittipos Giatgong, Yi Li, Neeraj Suri, Plamen Angelov

As the use of Deep Neural Networks (DNNs) becomes pervasive, their vulnerability to adversarial attacks and limitations in handling unseen classes poses significant challenges.

Adversarial Attack Classification +3

PUDD: Towards Robust Multi-modal Prototype-based Deepfake Detection

no code implementations22 Jun 2024 Alvaro Lopez Pellcier, Yi Li, Plamen Angelov

Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images.

DeepFake Detection Face Swapping +3

Federated Adversarial Learning for Robust Autonomous Landing Runway Detection

no code implementations22 Jun 2024 Yi Li, Plamen Angelov, Zhengxin Yu, Alvaro Lopez Pellicer, Neeraj Suri

As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks.

Federated Learning Lane Detection +1

Teleporter Theory: A General and Simple Approach for Modeling Cross-World Counterfactual Causality

no code implementations17 Jun 2024 Jiangmeng Li, Bin Qin, Qirui Ji, Yi Li, Wenwen Qiang, Jianwen Cao, Fanjiang Xu

Leveraging the development of structural causal model (SCM), researchers can establish graphical models for exploring the causal mechanisms behind machine learning techniques.

counterfactual

Revisiting Spurious Correlation in Domain Generalization

no code implementations17 Jun 2024 Bin Qin, Jiangmeng Li, Yi Li, Xuesong Wu, Yupeng Wang, Wenwen Qiang, Jianwen Cao

To this end, we explore to build a SCM for representation learning process and further conduct a thorough analysis of the mechanisms underlying spurious correlation.

Domain Generalization Representation Learning

Interventional Imbalanced Multi-Modal Representation Learning via $β$-Generalization Front-Door Criterion

no code implementations17 Jun 2024 Yi Li, Fei Song, Changwen Zheng, Jiangmeng Li, Fuchun Sun, Hui Xiong

However, our empirical explorations challenge the fundamental idea behind such behavior, and we further conclude that benchmark approaches suffer from certain defects: insufficient theoretical interpretability and limited exploration capability of discriminative knowledge.

Representation Learning

Continuous-Time Digital Twin with Analogue Memristive Neural Ordinary Differential Equation Solver

1 code implementation12 Jun 2024 Hegan Chen, Jichang Yang, Jia Chen, Songqi Wang, Shaocong Wang, Dingchen Wang, Xinyu Tian, Yifei Yu, Xi Chen, Yinan Lin, Yangu He, Xiaoshan Wu, Xinyuan Zhang, Ning Lin, Meng Xu, Yi Li, Xumeng Zhang, Zhongrui Wang, Han Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu

We experimentally validate our approach by developing a digital twin of the HP memristor, which accurately extrapolates its nonlinear dynamics, achieving a 4. 2-fold projected speedup and a 41. 4-fold projected decrease in energy consumption compared to state-of-the-art digital hardware, while maintaining an acceptable error margin.

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

no code implementations23 May 2024 Sheng-Jun Huang, Yi Li, Yiming Sun, Ying-Peng Tang

Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently.

Active Learning regression

HAGAN: Hybrid Augmented Generative Adversarial Network for Medical Image Synthesis

no code implementations8 May 2024 Zhihan Ju, Wanting Zhou, Longteng Kong, Yu Chen, Yi Li, Zhenan Sun, Caifeng Shan

However, due to the complexity of medical images and similar characteristics of different tissue cells, existing methods face great challenges in meeting their biological consistency.

Generative Adversarial Network Image Generation +1

PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation

1 code implementation4 May 2024 Ye Liu, Yue Xue, Daoyuan Wu, Yuqiang Sun, Yi Li, Miaolei Shi, Yang Liu

With recent advances in large language models (LLMs), this paper explores the potential of leveraging state-of-the-art LLMs, such as GPT-4, to transfer existing human-written properties (e. g., those from Certora auditing reports) and automatically generate customized properties for unknown code.

In-Context Learning Retrieval

Federated Graph Learning for EV Charging Demand Forecasting with Personalization Against Cyberattacks

no code implementations30 Apr 2024 Yi Li, Renyou Xie, Chaojie Li, Yi Wang, ZhaoYang Dong

To address these challenges, a federated graph learning approach involving multiple charging stations is proposed to collaboratively train a more generalized deep learning model for demand forecasting while capturing spatial correlations among various stations and enhancing robustness against potential attacks.

Demand Forecasting Federated Learning +2

Harmonic Machine Learning Models are Robust

no code implementations29 Apr 2024 Nicholas S. Kersting, Yi Li, Aman Mohanty, Oyindamola Obisesan, Raphael Okochu

We introduce Harmonic Robustness, a powerful and intuitive method to test the robustness of any machine-learning model either during training or in black-box real-time inference monitoring without ground-truth labels.

Cross-Temporal Spectrogram Autoencoder (CTSAE): Unsupervised Dimensionality Reduction for Clustering Gravitational Wave Glitches

1 code implementation23 Apr 2024 Yi Li, Yunan Wu, Aggelos K. Katsaggelos

In response to this challenge, we introduce the Cross-Temporal Spectrogram Autoencoder (CTSAE), a pioneering unsupervised method for the dimensionality reduction and clustering of gravitational wave glitches.

Clustering Dimensionality Reduction +1

Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model

1 code implementation8 Apr 2024 Jichang Yang, Hegan Chen, Jia Chen, Songqi Wang, Shaocong Wang, Yifei Yu, Xi Chen, Bo wang, Xinyuan Zhang, Binbin Cui, Ning Lin, Meng Xu, Yi Li, Xiaoxin Xu, Xiaojuan Qi, Zhongrui Wang, Xumeng Zhang, Dashan Shang, Han Wang, Qi Liu, Kwang-Ting Cheng, Ming Liu

Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.

Edge-computing

RoNet: Rotation-oriented Continuous Image Translation

no code implementations6 Apr 2024 Yi Li, Xin Xie, Lina Lei, Haiyan Fu, Yanqing Guo

The generation of smooth and continuous images between domains has recently drawn much attention in image-to-image (I2I) translation.

Translation

Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer

1 code implementation5 Apr 2024 Toru Shirakawa, Yi Li, Yulun Wu, Sky Qiu, YuXuan Li, Mingduo Zhao, Hiroyasu Iso, Mark van der Laan

We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings.

counterfactual Epidemiology +1

Spin: An Efficient Secure Computation Framework with GPU Acceleration

no code implementations4 Feb 2024 Wuxuan Jiang, Xiangjun Song, Shenbai Hong, Haijun Zhang, Wenxin Liu, Bo Zhao, Wei Xu, Yi Li

Accuracy and efficiency remain challenges for multi-party computation (MPC) frameworks.

Exploiting Hierarchical Interactions for Protein Surface Learning

1 code implementation17 Jan 2024 Yiqun Lin, Liang Pan, Yi Li, Ziwei Liu, Xiaomeng Li

In this paper, we present a principled framework based on deep learning techniques, namely Hierarchical Chemical and Geometric Feature Interaction Network (HCGNet), for protein surface analysis by bridging chemical and geometric features with hierarchical interactions.

Digital twin-assisted three-dimensional electrical capacitance tomography for multiphase flow imaging

no code implementations22 Dec 2023 Shengnan Wang, Yi Li, Zhou Chen, Yunjie Yang

Three-dimensional electrical capacitance tomography (3D-ECT) has shown promise for visualizing industrial multiphase flows.

Computational Efficiency

Random resistive memory-based deep extreme point learning machine for unified visual processing

no code implementations14 Dec 2023 Shaocong Wang, Yizhao Gao, Yi Li, Woyu Zhang, Yifei Yu, Bo wang, Ning Lin, Hegan Chen, Yue Zhang, Yang Jiang, Dingchen Wang, Jia Chen, Peng Dai, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Xiaoxin Xu, Hayden So, Zhongrui Wang, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu

Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.

Combined Scheduling, Memory Allocation and Tensor Replacement for Minimizing Off-Chip Data Accesses of DNN Accelerators

no code implementations30 Nov 2023 Yi Li, Aarti Gupta, Sharad Malik

We propose an optimization framework, named COSMA, for mapping DNNs to an accelerator that finds the optimal operator schedule, memory allocation and tensor replacement that minimizes the additional data accesses.

Neural Architecture Search Scheduling

Pruning random resistive memory for optimizing analogue AI

no code implementations13 Nov 2023 Yi Li, Songqi Wang, Yaping Zhao, Shaocong Wang, Woyu Zhang, Yangu He, Ning Lin, Binbin Cui, Xi Chen, Shiming Zhang, Hao Jiang, Peng Lin, Xumeng Zhang, Xiaojuan Qi, Zhongrui Wang, Xiaoxin Xu, Dashan Shang, Qi Liu, Kwang-Ting Cheng, Ming Liu

Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.

Audio Classification Image Segmentation +1

STOW: Discrete-Frame Segmentation and Tracking of Unseen Objects for Warehouse Picking Robots

no code implementations4 Nov 2023 Yi Li, Muru Zhang, Markus Grotz, Kaichun Mo, Dieter Fox

Segmentation and tracking of unseen object instances in discrete frames pose a significant challenge in dynamic industrial robotic contexts, such as distribution warehouses.

Object Rearrangement

Kernel Cox partially linear regression: building predictive models for cancer patients' survival

1 code implementation11 Oct 2023 Yaohua Rong, Sihai Dave Zhao, Xia Zheng, Yi Li

To accurately predict clinical outcomes, it is vital to build an accurate predictive model that relates patients' molecular profiles with patients' survival.

regression

City Foundation Models for Learning General Purpose Representations from OpenStreetMap

no code implementations1 Oct 2023 Pasquale Balsebre, Weiming Huang, Gao Cong, Yi Li

This can be attributed to the intrinsic heterogeneity of geospatial data, which encompasses different data types, including points, segments and regions, as well as multiple information modalities, such as a spatial position, visual characteristics and textual annotations.

Prefix-diffusion: A Lightweight Diffusion Model for Diverse Image Captioning

no code implementations10 Sep 2023 Guisheng Liu, Yi Li, Zhengcong Fei, Haiyan Fu, Xiangyang Luo, Yanqing Guo

While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems.

Denoising Diversity +1

CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No

1 code implementation ICCV 2023 Hualiang Wang, Yi Li, Huifeng Yao, Xiaomeng Li

Subsequently, we introduce two loss functions: the image-text binary-opposite loss and the text semantic-opposite loss, which we use to teach CLIPN to associate images with no prompts, thereby enabling it to identify unknown samples.

Negation Out-of-Distribution Detection +1

Morphology-inspired Unsupervised Gland Segmentation via Selective Semantic Grouping

1 code implementation22 Jul 2023 Qixiang Zhang, Yi Li, Cheng Xue, Xiaomeng Li

In this paper, we make a first attempt to explore a deep learning method for unsupervised gland segmentation, where no manual annotations are required.

Prognosis Segmentation +1

$\ell_p$-Regression in the Arbitrary Partition Model of Communication

no code implementations11 Jul 2023 Yi Li, Honghao Lin, David P. Woodruff

We consider the randomized communication complexity of the distributed $\ell_p$-regression problem in the coordinator model, for $p\in (0, 2]$.

regression

Learning the Positions in CountSketch

no code implementations11 Jun 2023 Yi Li, Honghao Lin, Simin Liu, Ali Vakilian, David P. Woodruff

We fix this issue and propose approaches for learning a sketching matrix for both low-rank approximation and Hessian approximation for second order optimization.

Channel Measurement, Modeling, and Simulation for 6G: A Survey and Tutorial

no code implementations26 May 2023 Jianhua Zhang, Jiaxin Lin, Pan Tang, Yuxiang Zhang, Huixin Xu, Tianyang Gao, Haiyang Miao, Zeyong Chai, Zhengfu Zhou, Yi Li, Huiwen Gong, Yameng Liu, Zhiqiang Yuan, Lei Tian, Shaoshi Yang, Liang Xia, Guangyi Liu, Ping Zhang

Then, a survey of the progress of the 6G channel research regarding the above five promising technologies is presented in terms of the latest measurement campaigns, new characteristics, modeling methods, and research prospects.

3D geometry Integrated sensing and communication +1

Evaluating Dynamic Conditional Quantile Treatment Effects with Applications in Ridesharing

no code implementations17 May 2023 Ting Li, Chengchun Shi, Zhaohua Lu, Yi Li, Hongtu Zhu

However, assessing dynamic quantile treatment effects (QTE) remains a challenge, particularly when dealing with data from ride-sourcing platforms that involve sequential decision-making across time and space.

Decision Making Sequential Decision Making

A Two-Stage Real Image Deraining Method for GT-RAIN Challenge CVPR 2023 Workshop UG$^{\textbf{2}}$+ Track 3

1 code implementation13 May 2023 Yun Guo, Xueyao Xiao, Xiaoxiong Wang, Yi Li, Yi Chang, Luxin Yan

Secondly, a transformer-based single image deraining network Uformer is implemented to pre-train on large real rain dataset and then fine-tuned on pseudo GT to further improve image restoration.

Image Restoration Single Image Deraining +2

Skeleton-based action analysis for ADHD diagnosis

no code implementations14 Apr 2023 YiChun Li, Yi Li, Rajesh Nair, Syed Mohsen Naqvi

Attention Deficit Hyperactivity Disorder (ADHD) is a common neurobehavioral disorder worldwide.

Action Analysis Action Recognition +3

A Closer Look at the Explainability of Contrastive Language-Image Pre-training

2 code implementations12 Apr 2023 Yi Li, Hualiang Wang, Yiqun Duan, Jiheng Zhang, Xiaomeng Li

These phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment.

Interactive Segmentation Language Modelling +5

Penalized Deep Partially Linear Cox Models with Application to CT Scans of Lung Cancer Patients

no code implementations9 Mar 2023 Yuming Sun, Jian Kang, Chinmay Haridas, Nicholas R. Mayne, Alexandra L. Potter, Chi-Fu Jeffrey Yang, David C. Christiani, Yi Li

The National Lung Screening Trial (NLST) employed computed tomography texture analysis, which provides objective measurements of texture patterns on CT scans, to quantify the mortality risks of lung cancer patients.

feature selection Survival Analysis +1

CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications

no code implementations1 Feb 2023 Gaolei Li, YuanYuan Zhao, Yi Li

Most existing studies on trustworthy FL aim to eliminate data poisoning threats that are produced by malicious clients, but in many cases, eliminating model poisoning attacks brought by fake servers is also an important objective.

Data Poisoning Decoder +4

Deep Learning of Semi-Competing Risk Data via a New Neural Expectation-Maximization Algorithm

no code implementations22 Dec 2022 Stephen Salerno, Yi Li

Prognostication for lung cancer, a leading cause of mortality, remains a complex task, as it needs to quantify the associations of risk factors and health events spanning a patient's entire life.

Survival Analysis

Spectrograms Are Sequences of Patches

1 code implementation28 Oct 2022 Leyi Zhao, Yi Li

Self-supervised pre-training models have been used successfully in several machine learning domains.

16k Self-Supervised Learning

Cross Task Neural Architecture Search for EEG Signal Classifications

1 code implementation1 Oct 2022 Yiqun Duan, Zhen Wang, Yi Li, Jianhang Tang, Yu-Kai Wang, Chin-Teng Lin

Recently, various neural network approaches have been proposed to improve the accuracy of EEG signal recognition.

EEG Emotion Recognition +2

Asynchronous and Error-prone Longitudinal Data Analysis via Functional Calibration

1 code implementation28 Sep 2022 Xinyue Chang, Yehua Li, Yi Li

In many longitudinal settings, time-varying covariates may not be measured at the same time as responses and are often prone to measurement error.

regression

Exploring Visual Interpretability for Contrastive Language-Image Pre-training

1 code implementation15 Sep 2022 Yi Li, Hualiang Wang, Yiqun Duan, Hang Xu, Xiaomeng Li

For this problem, we propose the Explainable Contrastive Language-Image Pre-training (ECLIP), which corrects the explainability via the Masked Max Pooling.

Retrieval text similarity

SSORN: Self-Supervised Outlier Removal Network for Robust Homography Estimation

no code implementations30 Aug 2022 Yi Li, Wenjie Pei, Zhenyu He

In this paper, we attempt to build a deep learning model that mimics all four steps in the traditional homography estimation pipeline.

Deep Learning Denoising +1

CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

1 code implementation17 Jul 2022 Xingyu Liu, Gu Wang, Yi Li, Xiangyang Ji

While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc.

Object Pose Estimation

Online Active Regression

no code implementations13 Jul 2022 Cheng Chen, Yi Li, Yiming Sun

Active regression considers a linear regression problem where the learner receives a large number of data points but can only observe a small number of labels.

regression

Online Easy Example Mining for Weakly-supervised Gland Segmentation from Histology Images

1 code implementation14 Jun 2022 Yi Li, Yiduo Yu, Yiwen Zou, Tianqi Xiang, Xiaomeng Li

Existing weakly-supervised semantic segmentation methods in computer vision achieve degenerative results for gland segmentation, since the characteristics and problems of glandular datasets are different from general object datasets.

Prognosis Segmentation +2

VALHALLA: Visual Hallucination for Machine Translation

1 code implementation CVPR 2022 Yi Li, Rameswar Panda, Yoon Kim, Chun-Fu, Chen, Rogerio Feris, David Cox, Nuno Vasconcelos

In particular, given a source sentence an autoregressive hallucination transformer is used to predict a discrete visual representation from the input text, and the combined text and hallucinated representations are utilized to obtain the target translation.

Hallucination Multimodal Machine Translation +2

GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis

no code implementations27 May 2022 Yushi Cao, Zhiming Li, Tianpei Yang, Hao Zhang, Yan Zheng, Yi Li, Jianye Hao, Yang Liu

In this paper, we combine the above two paradigms together and propose a novel Generalizable Logic Synthesis (GALOIS) framework to synthesize hierarchical and strict cause-effect logic programs.

Decision Making Deep Reinforcement Learning +3

UNet#: A UNet-like Redesigning Skip Connections for Medical Image Segmentation

no code implementations24 May 2022 Ledan Qian, Xiao Zhou, Yi Li, Zhongyi Hu

As an essential prerequisite for developing a medical intelligent assistant system, medical image segmentation has received extensive research and concentration from the neural network community.

Decoder Image Segmentation +4

Lassoed Tree Boosting

no code implementations22 May 2022 Alejandro Schuler, Yi Li, Mark van der Laan

Gradient boosting performs exceptionally in most prediction problems and scales well to large datasets.

regression

Multi-task Learning for Gaussian Graphical Regressions with High Dimensional Covariates

no code implementations21 May 2022 Jingfei Zhang, Yi Li

Gaussian graphical regression is a powerful means that regresses the precision matrix of a Gaussian graphical model on covariates, permitting the numbers of the response variables and covariates to far exceed the sample size.

Multi-Task Learning regression +1

Individualized Risk Assessment of Preoperative Opioid Use by Interpretable Neural Network Regression

1 code implementation7 May 2022 Yuming Sun, Jian Kang, Chad Brummett, Yi Li

Preoperative opioid use has been reported to be associated with higher preoperative opioid demand, worse postoperative outcomes, and increased postoperative healthcare utilization and expenditures.

Management regression

Unsupervised Image Deraining: Optimization Model Driven Deep CNN

no code implementations25 Mar 2022 Changfeng Yu, Yi Chang, Yi Li, XiLe Zhao, Luxin Yan

Consequently, we design an optimization model-driven deep CNN in which the unsupervised loss function of the optimization model is enforced on the proposed network for better generalization.

model Rain Removal

PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation

no code implementations23 Mar 2022 Yi Li, Jieming Zhu, Weiwen Liu, Liangcai Su, Guohao Cai, Qi Zhang, Ruiming Tang, Xi Xiao, Xiuqiang He

Specifically, PEAR not only captures feature-level and item-level interactions, but also models item contexts from both the initial ranking list and the historical clicked item list.

Recommendation Systems Re-Ranking

Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal

1 code implementation CVPR 2022 Yi Li, Yi Chang, Yan Gao, Changfeng Yu, Luxin Yan

Consequently, we perform inter-domain adaptation between the synthetic and real images by mutually exchanging the background and other two components.

Domain Adaptation Image Dehazing

Improving Video Model Transfer With Dynamic Representation Learning

no code implementations CVPR 2022 Yi Li, Nuno Vasconcelos

DRL is then formulated as an adversarial learning problem between the video and spatial models, with the objective of maximizing the dynamic score of learned spatiotemporal classifier.

Action Classification Knowledge Distillation +5

BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning

1 code implementation ICCV 2021 Zhirui Dai, Yuepeng Jiang, Yi Li, Bo Liu, Antoni B. Chan, Nuno Vasconcelos

A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed.

Camera Pose Estimation Pose Estimation

Pseudo-mask Matters in Weakly-supervised Semantic Segmentation

2 code implementations ICCV 2021 Yi Li, Zhanghui Kuang, Liyang Liu, Yimin Chen, Wayne Zhang

For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Generation to project the expanded CAMs to pseudo-mask based on a new metric indicating the importance of each class on each location, instead of the scores trained from binary classifiers.

Segmentation Weakly supervised Semantic Segmentation +1

Learning to Cluster via Same-Cluster Queries

no code implementations17 Aug 2021 Yi Li, Yan Song, Qin Zhang

We study the problem of learning to cluster data points using an oracle which can answer same-cluster queries.

Inference for High Dimensional Censored Quantile Regression

1 code implementation22 Jul 2021 Zhe Fei, Qi Zheng, Hyokyoung G. Hong, Yi Li

To our knowledge, there is little work available to draw inference on the effects of high dimensional predictors for censored quantile regression.

Epidemiology quantile regression +2

Single Pass Entrywise-Transformed Low Rank Approximation

no code implementations16 Jul 2021 Yifei Jiang, Yi Li, Yiming Sun, Jiaxin Wang, David P. Woodruff

A natural way to do this would be to simply apply $f$ to each entry of $A$, and then compute the matrix decomposition, but this requires storing all of $A$ as well as multiple passes over its entries.

Open-Ended Question Answering

Deep-learning-based Hyperspectral imaging through a RGB camera

no code implementations12 Jul 2021 Xinyu Gao, Tianlang Wang, Jing Yang, Jinchao Tao, Yanqing Qiu, Yanlong Meng, Banging Mao, Pengwei Zhou, Yi Li

Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection.

Deep Learning

Cross-Lingual Transfer Learning for Statistical Type Inference

no code implementations1 Jul 2021 Zhiming Li, Xiaofei Xie, Haoliang Li, Zhengzi Xu, Yi Li, Yang Liu

Hitherto statistical type inference systems rely thoroughly on supervised learning approaches, which require laborious manual effort to collect and label large amounts of data.

Code Summarization Cross-Lingual Transfer +4

Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images

1 code implementation20 Jun 2021 Haifeng Li, Yi Li, Guo Zhang, Ruoyun Liu, Haozhe Huang, Qing Zhu, Chao Tao

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing.

Contrastive Learning Segmentation +2

Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors

no code implementations20 May 2021 Jingyi Zhang, Huolan Zhu, Yongkai Chen, Chenguang Yang, Huimin Cheng, Yi Li, Wenxuan Zhong, Fang Wang

Background: Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate.

BIG-bench Machine Learning Classification +2

More Separable and Easier to Segment: A Cluster Alignment Method for Cross-Domain Semantic Segmentation

no code implementations7 May 2021 Shuang Wang, Dong Zhao, Yi Li, Chi Zhang, Yuwei Guo, Qi Zang, Biao Hou, Licheng Jiao

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation.

Clustering Segmentation +2

Learning-Augmented Sketches for Hessians

no code implementations24 Feb 2021 Yi Li, Honghao Lin, David P. Woodruff

We show how to design learned sketches for the Hessian in the context of second order methods.

Dimensionality Reduction Second-order methods

Growth and site-specific organization of micron-scale biomolecular devices on living mammalian cells

no code implementations19 Jan 2021 Sisi Jia, Siew Cheng Phua, Yuta Nihongaki, Yizeng Li, Michael Pacella, Yi Li, Abdul M. Mohammed, Sean Sun, Takanari Inoue, Rebecca Schulman

Mesoscale molecular assemblies on the cell surface, such as cilia and filopodia, integrate information, control transport and amplify signals.

Learning Discrete Adaptive Receptive Fields for Graph Convolutional Networks

no code implementations1 Jan 2021 Xiaojun Ma, Ziyao Li, Lingjun Xu, Guojie Song, Yi Li, Chuan Shi

To address this weakness, we introduce a novel framework of conducting graph convolutions, where nodes are discretely selected among multi-hop neighborhoods to construct adaptive receptive fields (ARFs).

Modified Gaussian Process Regression Models for Cyclic Capacity Prediction of Lithium-ion Batteries

no code implementations31 Dec 2020 Kailong Liu, Xiaosong Hu, Zhongbao Wei, Yi Li, Yan Jiang

Experimental results demonstrate that the modified Gaussian process regression model considering the battery electrochemical and empirical ageing signature outperforms other counterparts and is able to achieve satisfactory results for both one-step and multi-step predictions.

regression

Comments on large central charge $T\bar{T}$ deformed conformal field theory and cutoff AdS holography

no code implementations28 Dec 2020 Yi Li

For a modified version of cutoff AdS holography which is supposed to work only in the sector of classical pure gravity, we show that the flow equation of the metric and one point function of energy-momentum tensor in $T\bar{T}$ deformation corresponds to the flow equation of the boundary metric and Brown-York tensor on a cutoff surface in AdS space as the cutoff surface moves in the direction of normal geodesics.

High Energy Physics - Theory

Anomalous Hall and Nernst Effects in FeRh

no code implementations28 Dec 2020 Hilal Saglam, Changjiang Liu, Yi Li, Joseph Sklenar, Jonathan Gibbons, Deshun Hong, Vedat Karakas, John E. Pearson, Ozhan Ozatay, Wei zhang, Anand Bhattacharya, Axel Hoffmann

Antiferromagnets with tunable phase transitions are promising for future spintronics applications.

Materials Science

Robust Flat Bands with Tunable Energies in Honeycomb Superlattices

no code implementations14 Dec 2020 Zihao Qi, Eric Bobrow, Yi Li

Flat bands in lattice models have provided useful platforms for studying strong correlation and topological physics.

Mesoscale and Nanoscale Physics Strongly Correlated Electrons

Distinguishing limit of Bell states for any $n$-photon $D$-dimensional hyperentanglement

no code implementations26 Nov 2020 Chunzhen Li, Yi Li, Yongnan Li

There is a maximum number of distinguished Bell states, i. e. distinguising limit which is very important for increasing the channel capacity of quantum communications.

Quantum Physics

Lets Play Music: Audio-driven Performance Video Generation

no code implementations5 Nov 2020 Hao Zhu, Yi Li, Feixia Zhu, Aihua Zheng, Ran He

We propose a new task named Audio-driven Per-formance Video Generation (APVG), which aims to synthesizethe video of a person playing a certain instrument guided bya given music audio clip.

Video Generation

Learning Representations from Audio-Visual Spatial Alignment

no code implementations NeurIPS 2020 Pedro Morgado, Yi Li, Nuno Vasconcelos

To learn from these spatial cues, we tasked a network to perform contrastive audio-visual spatial alignment of 360{\deg} video and spatial audio.

Action Recognition Representation Learning +2

An Adversarial Attack Defending System for Securing In-Vehicle Networks

no code implementations25 Aug 2020 Yi Li, Jing Lin, Kaiqi Xiong

In a modern vehicle, there are over seventy Electronics Control Units (ECUs).

Adversarial Attack

Streaming Complexity of SVMs

no code implementations7 Jul 2020 Alexandr Andoni, Collin Burns, Yi Li, Sepideh Mahabadi, David P. Woodruff

We show that, for both problems, for dimensions $d=1, 2$, one can obtain streaming algorithms with space polynomially smaller than $\frac{1}{\lambda\epsilon}$, which is the complexity of SGD for strongly convex functions like the bias-regularized SVM, and which is known to be tight in general, even for $d=1$.

Graph Structural-topic Neural Network

1 code implementation25 Jun 2020 Qingqing Long, Yilun Jin, Guojie Song, Yi Li, Wei. Lin

Specifically, we build topic models upon graphs using anonymous walks and Graph Anchor LDA, an LDA variant that selects significant structural patterns first, so as to alleviate the complexity and generate structural topics efficiently.

Topic Models

Nearly Linear Row Sampling Algorithm for Quantile Regression

no code implementations ICML 2020 Yi Li, Ruosong Wang, Lin Yang, Hanrui Zhang

We give a row sampling algorithm for the quantile loss function with sample complexity nearly linear in the dimensionality of the data, improving upon the previous best algorithm whose sampling complexity has at least cubic dependence on the dimensionality.

quantile regression

Background Data Resampling for Outlier-Aware Classification

1 code implementation CVPR 2020 Yi Li, Nuno Vasconcelos

The problem of learning an image classifier that allows detection of out-of-distribution (OOD) examples, with the help of auxiliary background datasets, is studied.

Classification General Classification +2

Weakly Supervised Lesion Localization With Probabilistic-CAM Pooling

1 code implementation29 May 2020 Wenwu Ye, Jin Yao, Hui Xue, Yi Li

Localizing thoracic diseases on chest X-ray plays a critical role in clinical practices such as diagnosis and treatment planning.

Learning-Augmented Data Stream Algorithms

no code implementations ICLR 2020 Tanqiu Jiang, Yi Li, Honghao Lin, Yisong Ruan, David P. Woodruff

For estimating the $p$-th frequency moment for $0 < p < 2$ we obtain the first algorithms with optimal update time.

Cosmetic-Aware Makeup Cleanser

no code implementations20 Apr 2020 Yi Li, Huaibo Huang, Junchi Yu, Ran He, Tieniu Tan

Face verification aims at determining whether a pair of face images belongs to the same identity.

Face Parsing Face Verification +1

Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection

1 code implementation27 Mar 2020 Jianpeng Zhang, Yutong Xie, Guansong Pang, Zhibin Liao, Johan Verjans, Wenxin Li, Zongji Sun, Jian He, Yi Li, Chunhua Shen, Yong Xia

In this paper, we formulate the task of differentiating viral pneumonia from non-viral pneumonia and healthy controls into an one-class classification-based anomaly detection problem, and thus propose the confidence-aware anomaly detection (CAAD) model, which consists of a shared feature extractor, an anomaly detection module, and a confidence prediction module.

Binary Classification Classification +2

Informative Sample Mining Network for Multi-Domain Image-to-Image Translation

no code implementations ECCV 2020 Jie Cao, Huaibo Huang, Yi Li, Ran He, Zhenan Sun

The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models.

Image-to-Image Translation Informativeness +1

Evolving ab initio trading strategies in heterogeneous environments

1 code implementation19 Dec 2019 David Rushing Dewhurst, Yi Li, Alexander Bogdan, Jasmine Geng

Securities markets are quintessential complex adaptive systems in which heterogeneous agents compete in an attempt to maximize returns.

Path Planning Games

no code implementations30 Oct 2019 Yi Li, Yevgeniy Vorobeychik

Path planning is a fundamental and extensively explored problem in robotic control.

Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning

no code implementations21 Oct 2019 Ke Zhan, Shimiao Jiang, Yu Bai, Yi Li, Xu Liu, Zhuoran Xu

Eltwise layer is a commonly used structure in the multi-branch deep learning network.

Cross-Spectral Face Hallucination via Disentangling Independent Factors

no code implementations CVPR 2020 Boyan Duan, Chaoyou Fu, Yi Li, Xingguang Song, Ran He

The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR).

Face Alignment Face Hallucination +3

Data-Driven Neuron Allocation for Scale Aggregation Networks

1 code implementation CVPR 2019 Yi Li, Zhanghui Kuang, Yimin Chen, Wayne Zhang

The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated.

Image Classification object-detection +1

REPAIR: Removing Representation Bias by Dataset Resampling

1 code implementation CVPR 2019 Yi Li, Nuno Vasconcelos

An experimental set-up is also introduced to measure the bias of any dataset for a given representation, and the impact of this bias on the performance of recognition models.

Action Recognition Temporal Action Localization

Biphasic Learning of GANs for High-Resolution Image-to-Image Translation

no code implementations14 Apr 2019 Jie Cao, Huaibo Huang, Yi Li, Jingtuo Liu, Ran He, Zhenan Sun

In this work, we present a novel training framework for GANs, namely biphasic learning, to achieve image-to-image translation in multiple visual domains at $1024^2$ resolution.

Image-to-Image Translation Mutual Information Estimation +2

Estimation and Inference for High Dimensional Generalized Linear Models: A Splitting and Smoothing Approach

1 code implementation11 Mar 2019 Zhe Fei, Yi Li

In modern biomedical studies, focus has been shifted to estimate and explain the joint effects of high dimensional predictors (for example, molecular biomarkers) on a disease outcome (for example, onset of cancer).

Methodology

Detecting Lesion Bounding Ellipses With Gaussian Proposal Networks

1 code implementation25 Feb 2019 Yi Li

Instead of directly regressing the rotation angle of the ellipse as the common practice, GPN represents bounding ellipses as 2D Gaussian distributions on the image plain and minimizes the Kullback-Leibler (KL) divergence between the proposed Gaussian and the ground truth Gaussian for object localization.

Computed Tomography (CT) Lesion Detection +2

A Survey of Deep Facial Attribute Analysis

no code implementations26 Dec 2018 Xin Zheng, Yanqing Guo, Huaibo Huang, Yi Li, Ran He

Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes.

Attribute Survey

Arbitrary Talking Face Generation via Attentional Audio-Visual Coherence Learning

no code implementations17 Dec 2018 Hao Zhu, Huaibo Huang, Yi Li, Aihua Zheng, Ran He

Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image.

Talking Face Generation

DeepCruiser: Automated Guided Testing for Stateful Deep Learning Systems

no code implementations13 Dec 2018 Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Jianjun Zhao, Yang Liu

Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.

Deep Learning Speech-to-Text

Testing Matrix Rank, Optimally

no code implementations18 Oct 2018 Maria-Florina Balcan, Yi Li, David P. Woodruff, Hongyang Zhang

This improves upon the previous $O(d^2/\epsilon^2)$ bound (SODA'03), and bypasses an $\Omega(d^2/\epsilon^2)$ lower bound of (KDD'14) which holds if the algorithm is required to read a submatrix.

Cancer Metastasis Detection With Neural Conditional Random Field

1 code implementation19 Jun 2018 Yi Li, Wei Ping

Compared to the baseline method without considering spatial correlations, we show that the proposed NCRF framework obtains probability maps of patch predictions with better visual quality.

Cancer Metastasis Detection Medical Image Analysis +1

Covariance-Insured Screening

no code implementations17 May 2018 Kevin He, Jian Kang, Hyokyoung Grace Hong, Ji Zhu, Yanming Li, Huazhen Lin, Han Xu, Yi Li

Modern bio-technologies have produced a vast amount of high-throughput data with the number of predictors far greater than the sample size.

DeepIM: Deep Iterative Matching for 6D Pose Estimation

2 code implementations ECCV 2018 Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, Dieter Fox

Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality.

6D Pose Estimation 6D Pose Estimation using RGB +1

Enhanced Biologically Inspired Model for Image Recognition Based on a Novel Patch Selection Method with Moment

no code implementations27 Oct 2017 Yan-Feng Lu, Li-Hao Jia, Hong Qaio, Yi Li

Although the performance of BIM for image recognition is robust, it takes the randomly selected ways for the patch selection, which is sightless, and results in heavy computing burden.

Object Categorization

Anti-Makeup: Learning A Bi-Level Adversarial Network for Makeup-Invariant Face Verification

no code implementations12 Sep 2017 Yi Li, Lingxiao Song, Xiang Wu, Ran He, Tieniu Tan

This paper proposes a learning from generation approach for makeup-invariant face verification by introducing a bi-level adversarial network (BLAN).

Face Verification

Exploring Neural Transducers for End-to-End Speech Recognition

no code implementations24 Jul 2017 Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur, Yi Li, Hairong Liu, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu

In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition.

Language Modeling Language Modelling +2

Consensus measure of rankings

1 code implementation27 Apr 2017 Zhiwei Lin, Yi Li, Xiaolian Guo

The consensus measure can be used to evaluate rankings in many information systems, as quite often there is not ground truth available for evaluation.

Deformable Convolutional Networks

38 code implementations ICCV 2017 Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules.

Object Detection Semantic Segmentation +1

Classification with Ultrahigh-Dimensional Features

no code implementations4 Nov 2016 Yanming Li, Hyokyoung Hong, Jian Kang, Kevin He, Ji Zhu, Yi Li

Although much progress has been made in classification with high-dimensional features \citep{Fan_Fan:2008, JGuo:2010, CaiSun:2014, PRXu:2014}, classification with ultrahigh-dimensional features, wherein the features much outnumber the sample size, defies most existing work.

Classification General Classification

R-FCN: Object Detection via Region-based Fully Convolutional Networks

48 code implementations NeurIPS 2016 Jifeng Dai, Yi Li, Kaiming He, Jian Sun

In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.

image-classification Object +2

Instance-sensitive Fully Convolutional Networks

no code implementations29 Mar 2016 Jifeng Dai, Kaiming He, Yi Li, Shaoqing Ren, Jian Sun

In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.

Position Semantic Segmentation

Neural Self Talk: Image Understanding via Continuous Questioning and Answering

no code implementations10 Dec 2015 Yezhou Yang, Yi Li, Cornelia Fermuller, Yiannis Aloimonos

In this paper we consider the problem of continuously discovering image contents by actively asking image based questions and subsequently answering the questions being asked.

Question Answering Question Generation +2

Compositional Memory for Visual Question Answering

no code implementations18 Nov 2015 Aiwen Jiang, Fang Wang, Fatih Porikli, Yi Li

We then feed the episodes to a standard question answering module together with the contextual visual information and linguistic information.

Question Answering Visual Question Answering

Free-hand Sketch Synthesis with Deformable Stroke Models

no code implementations9 Oct 2015 Yi Li, Yi-Zhe Song, Timothy Hospedales, Shaogang Gong

We present a generative model which can automatically summarize the stroke composition of free-hand sketches of a given category.

Making Better Use of Edges via Perceptual Grouping

no code implementations CVPR 2015 Yonggang Qi, Yi-Zhe Song, Tao Xiang, Honggang Zhang, Timothy Hospedales, Yi Li, Jun Guo

We propose a perceptual grouping framework that organizes image edges into meaningful structures and demonstrate its usefulness on various computer vision tasks.

Learning-To-Rank Retrieval +1

Sketch-based 3D Shape Retrieval using Convolutional Neural Networks

no code implementations CVPR 2015 Fang Wang, Le Kang, Yi Li

Almost always in state of the art approaches a large amount of "best views" are computed for 3D models, with the hope that the query sketch matches one of these 2D projections of 3D models using predefined features.

3D Shape Classification 3D Shape Retrieval +2

DeepTrack: Learning Discriminative Feature Representations Online for Robust Visual Tracking

no code implementations28 Feb 2015 Hanxi Li, Yi Li, Fatih Porikli

In this work, we present an efficient and very robust tracking algorithm using a single Convolutional Neural Network (CNN) for learning effective feature representations of the target object, in a purely online manner.

Visual Tracking

Random Bits Regression: a Strong General Predictor for Big Data

no code implementations13 Jan 2015 Yi Wang, Yi Li, Momiao Xiong, Li Jin

To improve accuracy and speed of regressions and classifications, we present a data-based prediction method, Random Bits Regression (RBR).

BIG-bench Machine Learning regression

Physical Computing With No Clock to Implement the Gaussian Pyramid of SIFT Algorithm

no code implementations11 Aug 2014 Yi Li, Qi Wei, Fei Qiao, Huazhong Yang

In this paper, we propose an active circuit network to implement multi-scale Gaussian filter, which is also called Gaussian Pyramid in image preprocessing.

Is Rotation a Nuisance in Shape Recognition?

no code implementations CVPR 2014 Qiuhong Ke, Yi Li

and 3) how to use rotation unaware local features for rotation aware shape recognition?

Convolutional Neural Networks for No-Reference Image Quality Assessment

no code implementations CVPR 2014 Le Kang, Peng Ye, Yi Li, David Doermann

In this work we describe a Convolutional Neural Network (CNN) to accurately predict image quality without a reference image.

No-Reference Image Quality Assessment

Orientation Robust Text Line Detection in Natural Images

no code implementations CVPR 2014 Le Kang, Yi Li, David Doermann

In this paper, higher-order correlation clustering (HOCC) is used for text line detection in natural images.

Clustering graph partitioning +1

Beyond Physical Connections: Tree Models in Human Pose Estimation

no code implementations CVPR 2013 Fang Wang, Yi Li

Our method outperformed the state of the art on the LSP, both in the scenarios when the training images are from the same dataset and from the PARSE dataset.

Pose Estimation

Learning Visual Symbols for Parsing Human Poses in Images

no code implementations23 Apr 2013 Fang Wang, Yi Li

When the structure of the compositional parts is a tree, we derive an efficient approach to estimating human poses in images.

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