Search Results for author: Ke Zhang

Found 80 papers, 23 papers with code

vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving

no code implementations22 Jul 2024 Jiale Xu, Rui Zhang, Cong Guo, Weiming Hu, Zihan Liu, Feiyang Wu, Yu Feng, Shixuan Sun, Changxu Shao, Yuhong Guo, Junping Zhao, Ke Zhang, Minyi Guo, Jingwen Leng

This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM).

ModelMix: A New Model-Mixup Strategy to Minimize Vicinal Risk across Tasks for Few-scribble based Cardiac Segmentation

no code implementations19 Jun 2024 Ke Zhang, Vishal M. Patel

Pixel-level dense labeling is both resource-intensive and time-consuming, whereas weak labels such as scribble present a more feasible alternative to full annotations.

Cardiac Segmentation Segmentation

BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models

no code implementations17 Jun 2024 Xuefeng Hu, Ke Zhang, Min Sun, Albert Chen, Cheng-Hao Kuo, Ram Nevatia

Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains.

Image Classification Online Clustering +2

Semantically Consistent Video Inpainting with Conditional Diffusion Models

no code implementations30 Apr 2024 Dylan Green, William Harvey, Saeid Naderiparizi, Matthew Niedoba, Yunpeng Liu, Xiaoxuan Liang, Jonathan Lavington, Ke Zhang, Vasileios Lioutas, Setareh Dabiri, Adam Scibior, Berend Zwartsenberg, Frank Wood

Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames.

Optical Flow Estimation Video Inpainting

Couler: Unified Machine Learning Workflow Optimization in Cloud

1 code implementation12 Mar 2024 Xiaoda Wang, Yuan Tang, Tengda Guo, Bo Sang, Jingji Wu, Jian Sha, Ke Zhang, Jiang Qian, Mingjie Tang

This variety poses a challenge for end-users in terms of mastering different engine APIs.

Deep Efficient Private Neighbor Generation for Subgraph Federated Learning

no code implementations9 Jan 2024 Ke Zhang, Lichao Sun, Bolin Ding, Siu Ming Yiu, Carl Yang

Behemoth graphs are often fragmented and separately stored by multiple data owners as distributed subgraphs in many realistic applications.

Federated Learning Graph Mining

ASPEN: High-Throughput LoRA Fine-Tuning of Large Language Models with a Single GPU

1 code implementation5 Dec 2023 Zhengmao Ye, Dengchun Li, Jingqi Tian, Tingfeng Lan, Jie Zuo, Lei Duan, Hui Lu, Yexi Jiang, Jian Sha, Ke Zhang, Mingjie Tang

Transformer-based large language models (LLMs) have demonstrated outstanding performance across diverse domains, particularly when fine-turned for specific domains.

Large Language Model Scheduling

AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix

1 code implementation NeurIPS 2023 Yun Yue, Zhiling Ye, Jiadi Jiang, Yongchao Liu, Ke Zhang

Additionally, we introduce an auto-switching function that enables the preconditioning matrix to switch dynamically between Stochastic Gradient Descent (SGD) and the adaptive optimizer.

Recommendation Systems

Developing a Novel Image Marker to Predict the Clinical Outcome of Neoadjuvant Chemotherapy (NACT) for Ovarian Cancer Patients

no code implementations13 Sep 2023 Ke Zhang, Neman Abdoli, Patrik Gilley, Youkabed Sadri, Xuxin Chen, Theresa C. Thai, Lauren Dockery, Kathleen Moore, Robert S. Mannel, Yuchen Qiu

To address this clinical challenge, the purpose of this study is to develop a novel image marker to achieve high accuracy prognosis prediction of NACT at an early stage.

ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection

no code implementations ICCV 2023 Tao Tu, Shun-Po Chuang, Yu-Lun Liu, Cheng Sun, Ke Zhang, Donna Roy, Cheng-Hao Kuo, Min Sun

The results demonstrate that ImGeoNet outperforms the current state-of-the-art multi-view image-based method, ImVoxelNet, on all three datasets in terms of detection accuracy.

3D Object Detection object-detection

ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation

1 code implementation4 Aug 2023 Xuefeng Hu, Ke Zhang, Lu Xia, Albert Chen, Jiajia Luo, Yuyin Sun, Ken Wang, Nan Qiao, Xiao Zeng, Min Sun, Cheng-Hao Kuo, Ram Nevatia

Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e. g. achieving 76. 3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data.

Image Classification Language Modelling +2

Sharpness-Aware Minimization Revisited: Weighted Sharpness as a Regularization Term

1 code implementation25 May 2023 Yun Yue, Jiadi Jiang, Zhiling Ye, Ning Gao, Yongchao Liu, Ke Zhang

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization.

Multi-task Paired Masking with Alignment Modeling for Medical Vision-Language Pre-training

no code implementations13 May 2023 Ke Zhang, Yan Yang, Jun Yu, Hanliang Jiang, Jianping Fan, Qingming Huang, Weidong Han

To address this limitation, we propose a unified Med-VLP framework based on Multi-task Paired Masking with Alignment (MPMA) to integrate the cross-modal alignment task into the joint image-text reconstruction framework to achieve more comprehensive cross-modal interaction, while a Global and Local Alignment (GLA) module is designed to assist self-supervised paradigm in obtaining semantic representations with rich domain knowledge.

cross-modal alignment

Predict NAS Multi-Task by Stacking Ensemble Models using GP-NAS

no code implementations2 May 2023 Ke Zhang

In this track, Super Network builds a search space based on ViT-Base.

Construct sparse portfolio with mutual fund's favourite stocks in China A share market

no code implementations24 Apr 2023 Ke Zhang

Therefore, in order to get excess return from mutual fund industry, we use quantitative way to build the sparse portfolio that take advantage of favorite stocks by mutual fund in China A market.

DLRover-RM: Resource Optimization for Deep Recommendation Models Training in the Cloud

no code implementations4 Apr 2023 Qinlong Wang, Tingfeng Lan, Yinghao Tang, Ziling Huang, Yiheng Du, HaiTao Zhang, Jian Sha, Hui Lu, Yuanchun Zhou, Ke Zhang, Mingjie Tang

To overcome them, we introduce DLRover-RM, an elastic training framework for DLRMs designed to increase resource utilization and handle the instability of a cloud environment.


Adjust factor with volatility model using MAXFLAT low-pass filter and construct portfolio in China A share market

no code implementations29 Mar 2023 Ke Zhang

Our result shows adjust factors by MAXFLAT volatility model have better performance in both large cap and small cap universe than original factors or other risk adjust factors in China A share.


ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation

no code implementations12 Jan 2023 Ke Zhang, Xiahai Zhuang

Curating a large scale fully-annotated dataset can be both labour-intensive and expertise-demanding, especially for medical images.

Image Segmentation Medical Image Segmentation +3

CameraPose: Weakly-Supervised Monocular 3D Human Pose Estimation by Leveraging In-the-wild 2D Annotations

no code implementations8 Jan 2023 Cheng-Yen Yang, Jiajia Luo, Lu Xia, Yuyin Sun, Nan Qiao, Ke Zhang, Zhongyu Jiang, Jenq-Neng Hwang

By adding a camera parameter branch, any in-the-wild 2D annotations can be fed into our pipeline to boost the training diversity and the 3D poses can be implicitly learned by reprojecting back to 2D.

Data Augmentation Diversity +1

BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics

1 code implementation20 Dec 2022 Liang Ma, Shuyang Cao, Robert L. Logan IV, Di Lu, Shihao Ran, Ke Zhang, Joel Tetreault, Alejandro Jaimes

The proliferation of automatic faithfulness metrics for summarization has produced a need for benchmarks to evaluate them.

Multi-head Uncertainty Inference for Adversarial Attack Detection

no code implementations20 Dec 2022 YuQi Yang, Songyun Yang, Jiyang Xie. Zhongwei Si, Kai Guo, Ke Zhang, Kongming Liang

We adopt a multi-head architecture with multiple prediction heads (i. e., classifiers) to obtain predictions from different depths in the DNNs and introduce shallow information for the UI.

Adversarial Attack Detection Adversarial Defense

MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images

no code implementations6 Nov 2022 Junyi Qiu, Lei LI, Sihan Wang, Ke Zhang, Yinyin Chen, Shan Yang, Xiahai Zhuang

We therefore conducted extensive experiments to investigate the performance of the proposed method in dealing with such complex combinations of different CMR sequences.


Transformers Improve Breast Cancer Diagnosis from Unregistered Multi-View Mammograms

no code implementations21 Jun 2022 Xuxin Chen, Ke Zhang, Neman Abdoli, Patrik W. Gilley, Ximin Wang, Hong Liu, Bin Zheng, Yuchen Qiu

For this purpose, we employ local Transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts.

Image Registration

Deep Compatible Learning for Partially-Supervised Medical Image Segmentation

no code implementations18 Jun 2022 Ke Zhang, Xiahai Zhuang

To address the challenge, we propose a deep compatible learning (DCL) framework, which trains a single multi-label segmentation network using images with only partial structures annotated.

Image Segmentation Medical Image Segmentation +3

ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation

1 code implementation5 Jun 2022 Ke Zhang, Xiahai Zhuang

To tackle this problem, we propose a new scribble-guided method for cardiac segmentation, based on the Positive-Unlabeled (PU) learning framework and global consistency regularization, and termed as ShapePU.

Cardiac Segmentation Segmentation

Parallel Network with Channel Attention and Post-Processing for Carotid Arteries Vulnerable Plaque Segmentation in Ultrasound Images

no code implementations18 Apr 2022 Yanchao Yuan, Cancheng Li, Lu Xu, Ke Zhang, Yang Hua, Jicong Zhang

Test results show that the proposed method with dice loss function yields a Dice value of 0. 820, an IoU of 0. 701, Acc of 0. 969, and modified Hausdorff distance (MHD) of 1. 43 for 30 vulnerable cases of plaques, it outperforms some of the conventional CNN-based methods on these metrics.

Segmentation SSIM

InsCon:Instance Consistency Feature Representation via Self-Supervised Learning

no code implementations15 Mar 2022 Junwei Yang, Ke Zhang, Zhaolin Cui, Jinming Su, Junfeng Luo, Xiaolin Wei

On the other hand, InsCon introduces the pull and push of cell-instance, which utilizes cell consistency to enhance fine-grained feature representation for precise boundary localization.

Contrastive Learning Image Classification +6

CEKD:Cross Ensemble Knowledge Distillation for Augmented Fine-grained Data

no code implementations13 Mar 2022 Ke Zhang, Jin Fan, Shaoli Huang, Yongliang Qiao, Xiaofeng Yu, Feiwei Qin

We innovatively propose a cross distillation module to provide additional supervision to alleviate the noise problem, and propose a collaborative ensemble module to overcome the target conflict problem.

Data Augmentation Knowledge Distillation

CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision

1 code implementation CVPR 2022 Ke Zhang, Xiahai Zhuang

To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix.

Image Segmentation Medical Image Segmentation +2

Parallel Spatio-Temporal Attention-Based TCN for Multivariate Time Series Prediction

no code implementations2 Mar 2022 Fan Jin, Ke Zhang, Yipan Huang, Yifei Zhu, Baiping Chen

As industrial systems become more complex and monitoring sensors for everything from surveillance to our health become more ubiquitous, multivariate time series prediction is taking an important place in the smooth-running of our society.

Time Series Time Series Prediction

Virtual Adversarial Training for Semi-supervised Breast Mass Classification

no code implementations25 Jan 2022 Xuxin Chen, Ximin Wang, Ke Zhang, Kar-Ming Fung, Theresa C. Thai, Kathleen Moore, Robert S. Mannel, Hong Liu, Bin Zheng, Yuchen Qiu

This study aims to develop a novel computer-aided diagnosis (CAD) scheme for mammographic breast mass classification using semi-supervised learning.


Subgraph Federated Learning with Missing Neighbor Generation

1 code implementation NeurIPS 2021 Ke Zhang, Carl Yang, Xiaoxiao Li, Lichao Sun, Siu Ming Yiu

Graphs have been widely used in data mining and machine learning due to their unique representation of real-world objects and their interactions.

Federated Learning Graph Mining

A Review of Human Evaluation for Style Transfer

1 code implementation ACL (GEM) 2021 Eleftheria Briakou, Sweta Agrawal, Ke Zhang, Joel Tetreault, Marine Carpuat

However, in style transfer papers, we find that protocols for human evaluations are often underspecified and not standardized, which hampers the reproducibility of research in this field and progress toward better human and automatic evaluation methods.

Style Transfer

Ol\'a, Bonjour, Salve! XFORMAL: A Benchmark for Multilingual Formality Style Transfer

no code implementations NAACL 2021 Eleftheria Briakou, Di Lu, Ke Zhang, Joel Tetreault

We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian.

Formality Style Transfer Style Transfer

Recent advances and clinical applications of deep learning in medical image analysis

no code implementations27 May 2021 Xuxin Chen, Ximin Wang, Ke Zhang, Kar-Ming Fung, Theresa C. Thai, Kathleen Moore, Robert S. Mannel, Hong Liu, Bin Zheng, Yuchen Qiu

Deep learning has received extensive research interest in developing new medical image processing algorithms, and deep learning based models have been remarkably successful in a variety of medical imaging tasks to support disease detection and diagnosis.

Image Registration Lesion Classification

Structure Guided Lane Detection

1 code implementation12 May 2021 Jinming Su, Chao Chen, Ke Zhang, Junfeng Luo, Xiaoming Wei, Xiaolin Wei

Next, multi-level structural constraints are used to improve the perception of lanes.

Autonomous Driving Lane Detection

XFORMAL: A Benchmark for Multilingual Formality Style Transfer

1 code implementation8 Apr 2021 Eleftheria Briakou, Di Lu, Ke Zhang, Joel Tetreault

We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian.

Formality Style Transfer Style Transfer

Destruction of refractory carbon grains drives the final stage of proto-planetary disk chemistry

no code implementations29 Jan 2021 Arthur D. Bosman, Felipe Alarcon, Ke Zhang, Edwin A. Bergin

To elevate the volatile C/O ratio, additional carbon has to be released into the gas to enable an equilibrium chemistry under oxygen-poor conditions.

Earth and Planetary Astrophysics Solar and Stellar Astrophysics

Efficient erbium-doped thin-film lithium niobate waveguide amplifiers

no code implementations18 Jan 2021 Zhaoxi Chen, Qing Xu, Ke Zhang, Wing-Han Wong, De-Long Zhang, Edwin Yue-Bun Pun, Cheng Wang

Lithium niobate on insulator (LNOI) is an emerging photonic platform with great promises for future optical communications, nonlinear optics and microwave photonics.

Optics Applied Physics

Probing fast oscillating scalar dark matter with atoms and molecules

no code implementations2 Dec 2020 Dionysios Antypas, Oleg Tretiak, Ke Zhang, Antoine Garcon, Gilad Perez, Mikhail G. Kozlov, Stephan Schiller, Dmitry Budker

We discuss the WReSL experiment, report on progress towards improved measurements of rapid fundamental constant variations, and discuss the planned extension of the work to molecules, in which rapid variations of the nuclear mass can be sensitively searched for.

Atomic Physics High Energy Physics - Phenomenology

Edge Intelligence for Energy-efficient Computation Offloading and Resource Allocation in 5G Beyond

no code implementations17 Nov 2020 Yueyue Dai, Ke Zhang, Sabita Maharjan, Yan Zhang

In this paper, we utilize DRL to design an optimal computation offloading and resource allocation strategy for minimizing system energy consumption.

Anatomy Prior Based U-net for Pathology Segmentation with Attention

no code implementations17 Nov 2020 Yuncheng Zhou, Ke Zhang, Xinzhe Luo, Sihan Wang, Xiahai Zhuang

Pathological area segmentation in cardiac magnetic resonance (MR) images plays a vital role in the clinical diagnosis of cardiovascular diseases.

Anatomy Segmentation

Deep Reinforcement Learning for Stochastic Computation Offloading in Digital Twin Networks

no code implementations17 Nov 2020 Yueyue Dai, Ke Zhang, Sabita Maharjan, Yan Zhang

Then, we formulate the stochastic computation offloading and resource allocation problem to minimize the long-term energy efficiency.

reinforcement-learning Reinforcement Learning (RL)

Low-latency Federated Learning and Blockchain for Edge Association in Digital Twin empowered 6G Networks

no code implementations17 Nov 2020 Yunlong Lu, Xiaohong Huang, Ke Zhang, Sabita Maharjan, Yan Zhang

In this paper, we introduce the Digital Twin Wireless Networks (DTWN) by incorporating digital twins into wireless networks, to migrate real-time data processing and computation to the edge plane.

Federated Learning Multi-agent Reinforcement Learning

Secure Network Release with Link Privacy

no code implementations28 Sep 2020 Carl Yang, Haonan Wang, Ke Zhang, Lichao Sun

Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).

Graph Generation

MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism

1 code implementation9 Sep 2020 Ke Zhang, Yukun Su, Xiwang Guo, Liang Qi, Zhenbing Zhao

Facial attribute editing has mainly two objectives: 1) translating image from a source domain to a target one, and 2) only changing the facial regions related to a target attribute and preserving the attribute-excluding details.

Attribute Decoder +1

Secure Deep Graph Generation with Link Differential Privacy

1 code implementation1 May 2020 Carl Yang, Haonan Wang, Ke Zhang, Liang Chen, Lichao Sun

Many data mining and analytical tasks rely on the abstraction of networks (graphs) to summarize relational structures among individuals (nodes).

Graph Generation Link Prediction

Multi-Vehicle Routing Problems with Soft Time Windows: A Multi-Agent Reinforcement Learning Approach

no code implementations13 Feb 2020 Ke Zhang, Meng Li, Zhengchao Zhang, Xi Lin, Fang He

Multi-vehicle routing problem with soft time windows (MVRPSTW) is an indispensable constituent in urban logistics distribution systems.

Computational Efficiency Decoder +3

Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines

no code implementations17 Jan 2020 Zhenbing Zhao, Hongyu Qi, Yincheng Qi, Ke Zhang, Yongjie Zhai, Wenqing Zhao

In this paper, an automatic detection model called Automatic Visual Shape Clustering Network (AVSCNet) for pin-missing defect is constructed.

Clustering Defect Detection +2

Competing Ratio Loss for Discriminative Multi-class Image Classification

1 code implementation25 Dec 2019 Ke Zhang, Yurong Guo, Xinsheng Wang, Dongliang Chang, Zhenbing Zhao, Zhanyu Ma, Tony X. Han

However, during the training of the deep convolutional neural network, the value of NLLR is not always positive or negative, which severely affects the convergence of NLLR.

Age Estimation Classification +3

Unsupervised Detection of Sub-events in Large Scale Disasters

no code implementations13 Dec 2019 Chidubem Arachie, Manas Gaur, Sam Anzaroot, William Groves, Ke Zhang, Alejandro Jaimes

Given the large amounts of posts, a major challenge is identifying the information that is useful and actionable.

Nanoconfined, dynamic electrolyte gating and memory effects in multilayered graphene-based membranes

no code implementations29 Nov 2019 Jing Xiao, Hualin Zhan, Zaiquan Xu, Xiao Wang, Ke Zhang, Zhiyuan Xiong, George P. Simon, Zhe Liu, Dan Li

Multilayered graphene-based nanoporous membranes with electrolyte incorporated between individual sheets is a unique nano-heterostructure system in which nanoconfined electrons in graphene and ions confined in between sheets are intimately coupled throughout the entire membrane.

Mesoscale and Nanoscale Physics Materials Science Soft Condensed Matter Applied Physics Chemical Physics

Controllable Length Control Neural Encoder-Decoder via Reinforcement Learning

no code implementations17 Sep 2019 Junyi Bian, Baojun Lin, Ke Zhang, Zhaohui Yan, Hong Tang, Yonghe Zhang

Here, we denote a concept of Controllable Length Control (CLC) for the trade-off between length control capacity and semantic accuracy of the language generation model.

Decoder reinforcement-learning +3

Competing Ratio Loss for Discriminative Multi-class Image Classification

no code implementations31 Jul 2019 Ke Zhang, Xinsheng Wang, Yurong Guo, Zhenbing Zhao, Zhanyu Ma, Tony X. Han

A lot of studies of image classification based on deep convolutional neural network focus on the network structure to improve the image classification performance.

Age Estimation Classification +3

Hybrid Function Sparse Representation towards Image Super Resolution

1 code implementation11 Jun 2019 Junyi Bian, Baojun Lin, Ke Zhang

Based on the idea of making the magnification of function curve without losing its fidelity, we proposed a function based dictionary on sparse representation for super resolution, called hybrid function sparse representation (HFSR).

Image Super-Resolution

Retrospective Encoders for Video Summarization

no code implementations ECCV 2018 Ke Zhang, Kristen Grauman, Fei Sha

The key idea is to complement the discriminative losses with another loss which measures if the predicted summary preserves the same information as in the original video.

Metric Learning Video Summarization

Machine Learning at the Edge: A Data-Driven Architecture with Applications to 5G Cellular Networks

no code implementations23 Aug 2018 Michele Polese, Rittwik Jana, Velin Kounev, Ke Zhang, Supratim Deb, Michele Zorzi

Then, we will describe how the controllers can be used to run ML algorithms to predict the number of users in each base station, and a use case in which these predictions are exploited by a higher-layer application to route vehicular traffic according to network Key Performance Indicators (KPIs).

BIG-bench Machine Learning

Fine-Grained Age Estimation in the wild with Attention LSTM Networks

no code implementations26 May 2018 Ke Zhang, Na Liu, Xingfang Yuan, Xinyao Guo, Ce Gao, Zhenbing Zhao, Zhanyu Ma

Then, we fine-tune the ResNets or the RoR on the target age datasets to extract the global features of face images.

Ranked #4 on Age And Gender Classification on Adience Age (using extra training data)

Age And Gender Classification Age Estimation +1

The Sea Exploration Problem: Data-driven Orienteering on a Continuous Surface

no code implementations5 Feb 2018 João Pedro Pedroso, Alpar Vajk Kramer, Ke Zhang

This paper describes a problem arising in sea exploration, where the aim is to schedule the expedition of a ship for collecting information about the resources on the seafloor.

Gaussian Processes

Age Group and Gender Estimation in the Wild with Deep RoR Architecture

no code implementations9 Oct 2017 Ke Zhang, Ce Gao, Liru Guo, Miao Sun, Xingfang Yuan, Tony X. Han, Zhenbing Zhao, Baogang Li

In this paper, we propose a new CNN based method for age group and gender estimation leveraging Residual Networks of Residual Networks (RoR), which exhibits better optimization ability for age group and gender classification than other CNN architectures. Moreover, two modest mechanisms based on observation of the characteristics of age group are presented to further improve the performance of age estimation. In order to further improve the performance and alleviate over-fitting problem, RoR model is pre-trained on ImageNet firstly, and then it is fune-tuned on the IMDB-WIKI-101 data set for further learning the features of face images, finally, it is used to fine-tune on Adience data set.

Ranked #6 on Age And Gender Classification on Adience Age (using extra training data)

Age And Gender Classification Age and Gender Estimation +1

Pyramidal RoR for Image Classification

no code implementations1 Oct 2017 Ke Zhang, Liru Guo, Ce Gao, Zhenbing Zhao

The Residual Networks of Residual Networks (RoR) exhibits excellent performance in the image classification task, but sharply increasing the number of feature map channels makes the characteristic information transmission incoherent, which losses a certain of information related to classification prediction, limiting the classification performance.

Classification General Classification +1

Residual Networks of Residual Networks: Multilevel Residual Networks

1 code implementation9 Aug 2016 Ke Zhang, Miao Sun, Tony X. Han, Xingfang Yuan, Liru Guo, Tao Liu

This paper proposes a novel residual-network architecture, Residual networks of Residual networks (RoR), to dig the optimization ability of residual networks.

Image Classification

Video Summarization with Long Short-term Memory

1 code implementation26 May 2016 Ke Zhang, Wei-Lun Chao, Fei Sha, Kristen Grauman

We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots.

Domain Adaptation Structured Prediction +1

Summary Transfer: Exemplar-based Subset Selection for Video Summarization

no code implementations CVPR 2016 Ke Zhang, Wei-Lun Chao, Fei Sha, Kristen Grauman

Video summarization has unprecedented importance to help us digest, browse, and search today's ever-growing video collections.

Video Summarization

Gaming the Game: Honeypot Venues Against Cheaters in Location-based Social Networks

no code implementations16 Oct 2012 Konstantinos Pelechrinis, Prashant Krishnamurthy, Ke Zhang

LBSNs offer a number of conveniences to its participants, such as - but not limited to - a list of places in the vicinity of a user, recommendations for an area never explored before provided by other peers, tracking of friends, monetary rewards in the form of special deals from the venues visited as well as a cheap way of advertisement for the latter.

Social and Information Networks Cryptography and Security

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