Search Results for author: Min Xu

Found 93 papers, 24 papers with code

Training-free CryoET Tomogram Segmentation

1 code implementation8 Jul 2024 Yizhou Zhao, Hengwei Bian, Michael Mu, Mostofa R. Uddin, Zhenyang Li, Xiang Li, Tianyang Wang, Min Xu

In addition to prompt-based single-particle instance segmentation, our approach can automatically search for similar features, facilitating full tomogram semantic segmentation with only one prompt.

Contrastive Learning Cryogenic Electron Tomography +5

ISPO: An Integrated Ontology of Symptom Phenotypes for Semantic Integration of Traditional Chinese Medical Data

no code implementations8 Jul 2024 Zixin Shu, Rui Hua, Dengying Yan, Chenxia Lu, Ning Xu, Jun Li, Hui Zhu, Jia Zhang, Dan Zhao, Chenyang Hui, Junqiu Ye, Chu Liao, Qi Hao, Wen Ye, Cheng Luo, Xinyan Wang, Chuang Cheng, XiaoDong Li, Baoyan Liu, Xiaji Zhou, Runshun Zhang, Min Xu, Xuezhong Zhou

Methods: To construct an integrated ontology of symptom phenotypes (ISPO), we manually annotated classical TCM textbooks and large-scale Chinese electronic medical records (EMRs) to collect symptom terms with support from a medical text annotation system.

text annotation

Improving Knowledge Distillation in Transfer Learning with Layer-wise Learning Rates

no code implementations5 Jul 2024 Shirley Kokane, Mostofa Rafid Uddin, Min Xu

Contrary to these methods, in this work, we propose a novel layer-wise learning scheme that adjusts learning parameters per layer as a function of the differences in the Jacobian/Attention/Hessian of the output activations w. r. t.

Knowledge Distillation Transfer Learning

Differential Encoding for Improved Representation Learning over Graphs

no code implementations3 Jul 2024 Haimin Zhang, Jiahao Xia, Min Xu

The message-passing paradigm and the global attention mechanism fundamentally generate node embeddings based on information aggregated from a node's local neighborhood or from the whole graph.

Graph Representation Learning

Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection

no code implementations5 Jun 2024 Jash Dalvi, Ali Dabouei, Gunjan Dhanuka, Min Xu

Video anomaly detection aims to develop automated models capable of identifying abnormal events in surveillance videos.

Anomaly Detection Video Anomaly Detection

DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization

no code implementations27 May 2024 Mostofa Rafid Uddin, Min Xu

We demonstrate that the existing self-supervised methods with data augmentation result in the poor disentanglement of content and transformations in real-world scenarios.

Data Augmentation Disentanglement

Synergistic Global-space Camera and Human Reconstruction from Videos

no code implementations CVPR 2024 Yizhou Zhao, Tuanfeng Y. Wang, Bhiksha Raj, Min Xu, Jimei Yang, Chun-Hao Paul Huang

Specifically, we design Human-aware Metric SLAM to reconstruct metric-scale camera poses and scene point clouds using camera-frame HMR as a strong prior, addressing depth, scale, and dynamic ambiguities.

MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection

1 code implementation18 May 2024 Ximiao Zhang, Min Xu, Dehui Qiu, Ruixin Yan, Ning Lang, Xiuzhuang Zhou

To address this, we design a series of medical image anomaly synthesis tasks to simulate common disease patterns in medical imaging, transferring the powerful generalization capabilities of CLIP to the task of medical image anomaly detection.

Anomaly Detection Decision Making +1

Conditional Local Feature Encoding for Graph Neural Networks

no code implementations8 May 2024 Yongze Wang, Haimin Zhang, Qiang Wu, Min Xu

The key mechanism of current GNNs is message passing, where a node's feature is updated based on the information passing from its local neighbourhood.

Graph Classification Graph Regression +2

ERAGent: Enhancing Retrieval-Augmented Language Models with Improved Accuracy, Efficiency, and Personalization

no code implementations6 May 2024 Yunxiao Shi, Xing Zi, Zijing Shi, Haimin Zhang, Qiang Wu, Min Xu

The efficiency and personalization characteristics of ERAGent are supported by the Experiential Learner module which makes the AI assistant being capable of expanding its knowledge and modeling user profile incrementally.

Question Answering RAG +2

CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders

no code implementations15 Apr 2024 Chentianye Xu, Xueying Zhan, Min Xu

Cryo-electron microscopy (cryo-EM) emerges as a pivotal technology for determining the architecture of cells, viruses, and protein assemblies at near-atomic resolution.

3D Reconstruction Few-Shot Learning

RandAlign: A Parameter-Free Method for Regularizing Graph Convolutional Networks

no code implementations15 Apr 2024 Haimin Zhang, Min Xu

Intuitively, we can expect the generated embeddings become smooth asymptotically layerwisely, that is each layer of graph convolution generates a smoothed version of embeddings as compared to that generated by the previous layer.

Graph Representation Learning

Neighbour-level Message Interaction Encoding for Improved Representation Learning on Graphs

no code implementations15 Apr 2024 Haimin Zhang, Min Xu

To address this issue, we propose a neighbour-level message interaction information encoding method for improving graph representation learning.

Graph Representation Learning

Optimal convex $M$-estimation via score matching

no code implementations25 Mar 2024 Oliver Y. Feng, Yu-Chun Kao, Min Xu, Richard J. Samworth

As an example of a non-log-concave setting, for Cauchy errors, the optimal convex loss function is Huber-like, and our procedure yields an asymptotic efficiency greater than 0. 87 relative to the oracle maximum likelihood estimator of the regression coefficients that uses knowledge of this error distribution; in this sense, we obtain robustness without sacrificing much efficiency.


Uncertainty-Aware Adapter: Adapting Segment Anything Model (SAM) for Ambiguous Medical Image Segmentation

no code implementations16 Mar 2024 Mingzhou Jiang, Jiaying Zhou, Junde Wu, Tianyang Wang, Yueming Jin, Min Xu

The Segment Anything Model (SAM) gained significant success in natural image segmentation, and many methods have tried to fine-tune it to medical image segmentation.

Image Segmentation Medical Image Segmentation +3

RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection

1 code implementation CVPR 2024 Ximiao Zhang, Min Xu, Xiuzhuang Zhou

Self-supervised feature reconstruction methods have shown promising advances in industrial image anomaly detection and localization.

Anomaly Detection feature selection

Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition

no code implementations8 Mar 2024 Junde Wu, Jiayuan Zhu, Min Xu, Yueming Jin

Some visual recognition tasks are more challenging then the general ones as they require professional categories of images.

Explainable Models object-detection +1

Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation

no code implementations6 Mar 2024 Li Wang, Min Xu, Quangui Zhang, Yunxiao Shi, Qiang Wu

Building upon this insight, we propose a disentangled encoder that focuses on disentangling user and item embeddings into interest and social influence embeddings.

Causal Inference Disentanglement +1

A Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation

no code implementations6 Mar 2024 Li Wang, Lei Sang, Quangui Zhang, Qiang Wu, Min Xu

Furthermore, we introduce a privacy-preserving decoder to mitigate user privacy leakage during knowledge transfer.

Contrastive Learning Decoder +2

Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning

no code implementations10 Dec 2023 Zaber Ibn Abdul Hakim, Najibul Haque Sarker, Rahul Pratap Singh, Bishmoy Paul, Ali Dabouei, Min Xu

Orthogonal to the previous approaches to this limitation, we postulate that understanding the significance of the sentence components according to the target task can potentially enhance the performance of the models.

Language Modelling Large Language Model +5

Multi-dimensional Fusion and Consistency for Semi-supervised Medical Image Segmentation

no code implementations12 Sep 2023 Yixing Lu, Zhaoxin Fan, Min Xu

In this paper, we introduce a novel semi-supervised learning framework tailored for medical image segmentation.

Image Segmentation Semantic Segmentation +1

One-Prompt to Segment All Medical Images

2 code implementations CVPR 2024 Junde Wu, Jiayuan Zhu, Yueming Jin, Min Xu

Tested on 14 previously unseen datasets, the One-Prompt Model showcases superior zero-shot segmentation capabilities, outperforming a wide range of related methods.

Image Segmentation Interactive Segmentation +6

Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation

3 code implementations25 Apr 2023 Junde Wu, Wei Ji, Yuanpei Liu, Huazhu Fu, Min Xu, Yanwu Xu, Yueming Jin

In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation.

Image Segmentation Medical Image Segmentation +2

Vital Sign Monitoring in Dynamic Environment via mmWave Radar and Camera Fusion

no code implementations20 Apr 2023 Yingqi Wang, Zhongqin Wang, J. Andrew Zhang, Haimin Zhang, Min Xu

Contact-free vital sign monitoring, which uses wireless signals for recognizing human vital signs (i. e, breath and heartbeat), is an attractive solution to health and security.

Multimodal Hyperspectral Image Classification via Interconnected Fusion

no code implementations2 Apr 2023 Lu Huo, Jiahao Xia, Leijie Zhang, Haimin Zhang, Min Xu

More specifically, they overlook the contextual information across modalities of HSI and LiDAR and the intra-modality characteristics of LiDAR.

Classification Decoder +1

CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting

1 code implementation11 Mar 2023 Simon Graham, Quoc Dang Vu, Mostafa Jahanifar, Martin Weigert, Uwe Schmidt, Wenhua Zhang, Jun Zhang, Sen yang, Jinxi Xiang, Xiyue Wang, Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch, Lihao Liu, Chenyang Hong, Angelica I. Aviles-Rivero, Ayushi Jain, Heeyoung Ahn, Yiyu Hong, Hussam Azzuni, Min Xu, Mohammad Yaqub, Marie-Claire Blache, Benoît Piégu, Bertrand Vernay, Tim Scherr, Moritz Böhland, Katharina Löffler, Jiachen Li, Weiqin Ying, Chixin Wang, Dagmar Kainmueller, Carola-Bibiane Schönlieb, Shuolin Liu, Dhairya Talsania, Yughender Meda, Prakash Mishra, Muhammad Ridzuan, Oliver Neumann, Marcel P. Schilling, Markus Reischl, Ralf Mikut, Banban Huang, Hsiang-Chin Chien, Ching-Ping Wang, Chia-Yen Lee, Hong-Kun Lin, Zaiyi Liu, Xipeng Pan, Chu Han, Jijun Cheng, Muhammad Dawood, Srijay Deshpande, Raja Muhammad Saad Bashir, Adam Shephard, Pedro Costa, João D. Nunes, Aurélio Campilho, Jaime S. Cardoso, Hrishikesh P S, Densen Puthussery, Devika R G, Jiji C V, Ye Zhang, Zijie Fang, Zhifan Lin, Yongbing Zhang, Chunhui Lin, Liukun Zhang, Lijian Mao, Min Wu, Vi Thi-Tuong Vo, Soo-Hyung Kim, Taebum Lee, Satoshi Kondo, Satoshi Kasai, Pranay Dumbhare, Vedant Phuse, Yash Dubey, Ankush Jamthikar, Trinh Thi Le Vuong, Jin Tae Kwak, Dorsa Ziaei, Hyun Jung, Tianyi Miao, David Snead, Shan E Ahmed Raza, Fayyaz Minhas, Nasir M. Rajpoot

Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.

Nuclear Segmentation Segmentation +2

BenchDirect: A Directed Language Model for Compiler Benchmarks

no code implementations2 Mar 2023 Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather

We improve this with BenchDirect which utilizes a directed LM that infills programs by jointly observing source code context and the compiler features that are targeted.

Active Learning Language Modelling

MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer

2 code implementations19 Jan 2023 Junde Wu, Wei Ji, Huazhu Fu, Min Xu, Yueming Jin, Yanwu Xu

To effectively integrate these two cutting-edge techniques for the Medical image segmentation, we propose a novel Transformer-based Diffusion framework, called MedSegDiff-V2.

Image Generation Image Segmentation +3

Confidence-Calibrated Face and Kinship Verification

2 code implementations25 Oct 2022 Min Xu, Ximiao Zhang, Xiuzhuang Zhou

In this paper, we investigate the problem of prediction confidence in face and kinship verification.

Kinship Verification

BenchPress: A Deep Active Benchmark Generator

1 code implementation13 Aug 2022 Foivos Tsimpourlas, Pavlos Petoumenos, Min Xu, Chris Cummins, Kim Hazelwood, Ajitha Rajan, Hugh Leather

We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code.

Active Learning

Deep Active Learning with Noise Stability

no code implementations26 May 2022 Xingjian Li, Pengkun Yang, Yangcheng Gu, Xueying Zhan, Tianyang Wang, Min Xu, Chengzhong Xu

We provide theoretical analyses by leveraging the small Gaussian noise theory and demonstrate that our method favors a subset with large and diverse gradients.

Active Learning

Dataset Pruning: Reducing Training Data by Examining Generalization Influence

no code implementations19 May 2022 Shuo Yang, Zeke Xie, Hanyu Peng, Min Xu, Mingming Sun, Ping Li

To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap.

Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning

1 code implementation CVPR 2022 Jiahao Xia, Weiwei qu, Wenjian Huang, JianGuo Zhang, Xi Wang, Min Xu

The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism.

Face Alignment Relation +1

Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification

no code implementations3 Mar 2022 Hussam Azzuni, Muhammad Ridzuan, Min Xu, Mohammad Yaqub

Nuclei segmentation and classification is the first and most crucial step that is utilized for many different microscopy medical analysis applications.

Instance Segmentation Segmentation +1

Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations

no code implementations CVPR 2022 Mostofa Rafid Uddin, Gregory Howe, Xiangrui Zeng, Min Xu

Harmony leverages a simple cross-contrastive learning framework with multiple explicitly parameterized latent representations to disentangle content from transformations.

Contrastive Learning Disentanglement

Boosting Active Learning via Improving Test Performance

1 code implementation10 Dec 2021 Tianyang Wang, Xingjian Li, Pengkun Yang, Guosheng Hu, Xiangrui Zeng, Siyu Huang, Cheng-Zhong Xu, Min Xu

In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.

Active Learning Electron Tomography +2

Objects in Semantic Topology

no code implementations ICLR 2022 Shuo Yang, Peize Sun, Yi Jiang, Xiaobo Xia, Ruiheng Zhang, Zehuan Yuan, Changhu Wang, Ping Luo, Min Xu

A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.

Incremental Learning Language Modelling +3

Task-wise Split Gradient Boosting Trees for Multi-center Diabetes Prediction

1 code implementation16 Aug 2021 Mingcheng Chen, Zhenghui Wang, Zhiyun Zhao, Weinan Zhang, Xiawei Guo, Jian Shen, Yanru Qu, Jieli Lu, Min Xu, Yu Xu, Tiange Wang, Mian Li, Wei-Wei Tu, Yong Yu, Yufang Bi, Weiqing Wang, Guang Ning

To tackle the above challenges, we employ gradient boosting decision trees (GBDT) to handle data heterogeneity and introduce multi-task learning (MTL) to solve data insufficiency.

Diabetes Prediction Multi-Task Learning

A Hybrid Vehicle Platoon for Connected and Automated Vehicles: Formulation, Stability Analysis, and Applications

no code implementations23 Jul 2021 Yuan Zheng, Min Xu, Shining Wu, Shuaian Wang

The findings have demonstrated the merits of the combined implementation of CTG and CS policy in enhancing the performance and applicability of the platoon system for CAVs.

Disentangling semantic features of macromolecules in Cryo-Electron Tomography

no code implementations27 Jun 2021 Kai Yi, Jianye Pang, Yungeng Zhang, Xiangrui Zeng, Min Xu

Cryo-electron tomography (Cryo-ET) is a 3D imaging technique that enables the systemic study of shape, abundance, and distribution of macromolecular structures in single cells in near-atomic resolution.

Electron Tomography

Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

no code implementations27 May 2021 Shuo Yang, Erkun Yang, Bo Han, Yang Liu, Min Xu, Gang Niu, Tongliang Liu

Motivated by that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i. e., Bayes-label transition matrix (BLTM)) and learn a classifier to predict Bayes optimal labels.

An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking

no code implementations13 Mar 2021 Jiahao Xia, Haimin Zhang, Shiping Wen, Shuo Yang, Min Xu

Moreover, we generate a cheap heatmap based on the face alignment result and fuse it with features to improve the performance of the other two tasks.

Face Alignment Face Detection +1

Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations

no code implementations8 Mar 2021 Haimin Zhang, Min Xu

Based on this observation, we propose a method for counteracting adversarial perturbations to improve adversarial robustness.

Adversarial Robustness

SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks

1 code implementation20 Feb 2021 Haimin Zhang, Min Xu, Guoqiang Zhang, Kenta Niwa

We show that applying stochastic scaling at the gradient level is complementary to that applied at the feature level to improve the overall performance.

Graph Learning

Free Lunch for Few-shot Learning: Distribution Calibration

6 code implementations ICLR 2021 Shuo Yang, Lu Liu, Min Xu

In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples, then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier.

Few-Shot Learning

End-to-End Robust Joint Unsupervised Image Alignment and Clustering

no code implementations ICCV 2021 Xiangrui Zeng, Gregory Howe, Min Xu

To our knowledge, Jim-Net is the first end-to-end model that can simultaneously align and cluster images, which significantly improves the performance as compared to performing each task alone.

Clustering Electron Tomography

Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data

no code implementations28 Nov 2020 Nanqing Dong, Michael Kampffmeyer, Xiaodan Liang, Min Xu, Irina Voiculescu, Eric P. Xing

To bridge the methodological gaps in partially supervised learning (PSL) under data scarcity, we propose Vicinal Labels Under Uncertainty (VLUU), a simple yet efficient framework utilizing the human structure similarity for partially supervised medical image segmentation.

Data Augmentation Image Segmentation +5

Weight Encode Reconstruction Network for Computed Tomography in a Semi-Case-Wise and Learning-Based Way

no code implementations2 Oct 2020 Hujie Pan, Xuesong Li, Min Xu

In the generalization test of the model, the encoder is transferable from a voxel set with complex structure to the unseen cases without the deduction of the accuracy.


Experimental Analysis of Legendre Decomposition in Machine Learning

no code implementations12 Aug 2020 Jianye Pang, Kai Yi, Wanguang Yin, Min Xu

In this technical report, we analyze Legendre decomposition for non-negative tensor in theory and application.

BIG-bench Machine Learning Clustering

Few shot domain adaptation for in situ macromolecule structural classification in cryo-electron tomograms

no code implementations30 Jul 2020 Liangyong Yu, Ran Li, Xiangrui Zeng, Hongyi Wang, Jie Jin, Ge Yang, Rui Jiang, Min Xu

Motivation: Cryo-Electron Tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at sub-molecular resolution.

Classification Domain Adaptation +2

SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking

no code implementations17 Mar 2020 Yihao Luo, Min Xu, Caihong Yuan, Xiang Cao, Liangqi Zhang, Yan Xu, Tianjiang Wang, Qi Feng

Recently spiking neural networks (SNNs), the third-generation of neural networks has shown remarkable capabilities of energy-efficient computing, which is a promising alternative for deep neural networks (DNNs) with high energy consumption.

Image Classification Visual Object Tracking

Single-View 3D Object Reconstruction from Shape Priors in Memory

no code implementations CVPR 2021 Shuo Yang, Min Xu, Haozhe Xie, Stuart Perry, Jiahao Xia

Inspired by this, we propose a novel method, named Mem3D, that explicitly constructs shape priors to supplement the missing information in the image.

3D Object Reconstruction 3D Reconstruction +4

AITom: Open-source AI platform for cryo-electron tomography data analysis

2 code implementations8 Nov 2019 Xiangrui Zeng, Min Xu

Cryo-electron tomography (cryo-ET) is an emerging technology for the 3D visualization of structural organizations and interactions of subcellular components at near-native state and sub-molecular resolution.

Electron Tomography

A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis

no code implementations5 Oct 2019 Wei Wu, Xukun Li, Peng Du, Guanjing Lang, Min Xu, Kaijin Xu, Lanjuan Li

The best model was selected to annotate the spatial location of lesions and classify them into miliary, infiltrative, caseous, tuberculoma and cavitary types simultaneously. Then the Noisy-Or Bayesian function was used to generate an overall infection probability. Finally, a quantitative diagnostic report was exported. The results showed that the recall and precision rates, from the perspective of a single lesion region of PTB, were 85. 9% and 89. 2% respectively.

Computed Tomography (CT) Decision Making +1

Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection

1 code implementation ICCV 2019 Yingyue Xu, Dan Xu, Xiaopeng Hong, Wanli Ouyang, Rongrong Ji, Min Xu, Guoying Zhao

We formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-prediction, from the coarse scale to the finer scale, to update the features and the corresponding predictions.

object-detection RGB Salient Object Detection +1

Visual Analytics of Student Learning Behaviors on K-12 Mathematics E-learning Platforms

no code implementations7 Sep 2019 Meng Xia, Huan Wei, Min Xu, Leo Yu Ho Lo, Yong Wang, Rong Zhang, Huamin Qu

With increasing popularity in online learning, a surge of E-learning platforms have emerged to facilitate education opportunities for k-12 (from kindergarten to 12th grade) students and with this, a wealth of information on their learning logs are getting recorded.


Improving Utility and Security of the Shuffler-based Differential Privacy

1 code implementation30 Aug 2019 Tianhao Wang, Bolin Ding, Min Xu, Zhicong Huang, Cheng Hong, Jingren Zhou, Ninghui Li, Somesh Jha

When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator.

Deep Learning-Based Strategy for Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography

no code implementations27 Aug 2019 Ziqian Luo, Xiangrui Zeng, Zhipeng Bao, Min Xu

Deep learning model trained by imbalanced data may not work satisfactorily since it could be determined by major classes and thus may ignore the classes with small amount of data.

Classification Electron Tomography +1

Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization

no code implementations11 Jun 2018 Haimin Zhang, Min Xu

This architecture forces the network to learn discriminative class-specific features by analyzing and comparing two input images.

Image Classification

Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations

no code implementations31 May 2018 Guannan Zhao, Bo Zhou, Kaiwen Wang, Rui Jiang, Min Xu

The weighted feature maps are combined to produce a heatmap that highlights the important regions in the image for predicting the target concept.

Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography

no code implementations16 May 2018 Chang Liu, Xiangrui Zeng, Kaiwen Wang, Qiang Guo, Min Xu

Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells.

Classification Diversity +4

Image-derived generative modeling of pseudo-macromolecular structures - towards the statistical assessment of Electron CryoTomography template matching

no code implementations12 May 2018 Kai Wen Wang, Xiangrui Zeng, Xiaodan Liang, Zhiguang Huo, Eric P. Xing, Min Xu

Cellular Electron CryoTomography (CECT) is a 3D imaging technique that captures information about the structure and spatial organization of macromolecular complexes within single cells, in near-native state and at sub-molecular resolution.

Generative Adversarial Network Template Matching +1

An integration of fast alignment and maximum-likelihood methods for electron subtomogram averaging and classification

no code implementations4 Apr 2018 Yixiu Zhao, Xiangrui Zeng, Qiang Guo, Min Xu

Existing subtomogram alignment based methods are prone to the missing wedge effects and low signal-to-noise ratio (SNR).

General Classification

AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding

no code implementations24 Mar 2018 Lei Sang, Min Xu, Shengsheng Qian, Xindong Wu

Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as first- and second-order proximity of nodes, ignoring the fact that different scales play different roles in the embedding learning.

Network Embedding

Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms

no code implementations12 Feb 2018 Chang Liu, Xiangrui Zeng, Ruogu Lin, Xiaodan Liang, Zachary Freyberg, Eric Xing, Min Xu

Cellular Electron Cryo-Tomography (CECT) is a powerful imaging technique for the 3D visualization of cellular structure and organization at submolecular resolution.

Decoder Segmentation +1

Feature Decomposition Based Saliency Detection in Electron Cryo-Tomograms

no code implementations31 Jan 2018 Bo Zhou, Qiang Guo, Xiangrui Zeng, Min Xu

To complement and speed up existing segmentation methods, it is desirable to develop a generic cell component segmentation method that is 1) not specific to particular types of cellular components, 2) able to segment unknown cellular components, 3) fully unsupervised and does not rely on the availability of training data.

Saliency Detection Segmentation

Experience enrichment based task independent reward model

no code implementations21 May 2017 Min Xu

For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks.

reinforcement-learning Reinforcement Learning (RL)

Learning Multi-level Deep Representations for Image Emotion Classification

no code implementations22 Nov 2016 Tianrong Rao, Min Xu, Dong Xu

The proposed MldrNet combines deep representations of different levels, i. e. image semantics, image aesthetics, and low-level visual features to effectively classify the emotion types of different kinds of images, such as abstract paintings and web images.

Classification Emotion Classification +1

Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos

no code implementations20 Mar 2016 Haimin Zhang, Min Xu

By this way, static image features extracted from a pre-trained deep CNN and temporal information represented by DFT features are jointly considered for video emotion recognition.

Emotion Classification Video Emotion Recognition

Integrative analysis of gene expression and phenotype data

no code implementations29 Jun 2015 Min Xu

We propose a method of automated multi-dimensional profiling which uses gene expression similarity.

Experimental Design

Automatic tracking of protein vesicles

no code implementations5 Jun 2015 Min Xu

In this thesis, we formulate such tracking problem as video object tracking problem, and design a dynamic programming method for tracking single object.

Multiple Object Tracking Object +1

Gene selection for cancer classification using a hybrid of univariate and multivariate feature selection methods

no code implementations5 Jun 2015 Min Xu, Rudy Setiono

Various approaches to gene selection for cancer classification based on microarray data can be found in the literature and they may be grouped into two categories: univariate methods and multivariate methods.

feature selection General Classification

Global Gene Expression Analysis Using Machine Learning Methods

no code implementations5 Jun 2015 Min Xu

The large amount of expression data generated by this technology makes the study of certain complex biological problems possible and machine learning methods are playing a crucial role in the analysis process.

BIG-bench Machine Learning Classification +3

Estimation Bias in Multi-Armed Bandit Algorithms for Search Advertising

no code implementations NeurIPS 2013 Min Xu, Tao Qin, Tie-Yan Liu

In search advertising, the search engine needs to select the most profitable advertisements to display, which can be formulated as an instance of online learning with partial feedback, also known as the stochastic multi-armed bandit (MAB) problem.

Selection bias

Noise Thresholds for Spectral Clustering

no code implementations NeurIPS 2011 Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy, Aarti Singh

Although spectral clustering has enjoyed considerable empirical success in machine learning, its theoretical properties are not yet fully developed.


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