检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Qing, Zhiwu Huang, Ziyuan Zhang, Shiwei Tang, Mingqian Gao, Changxin Ang, Marcelo H. Jin, Rong Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China ARC National University of Singapore Singapore Alibaba Group China

The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid trivial solutions, augmentation plays an important role in generating different views, among which random cropping is shown to be effective for the model to learn a generalized and robust representation. Commonly used random crop operation keeps the distribution of the difference between two views unchanged along the training process. In this work, we show that adaptively controlling the disparity between two augmented views along the training process enhances the quality of the learned representations. Specifically, we present a parametric cubic cropping operation, ParamCrop, for video contrastive learning, which automatically crops a 3D cubic by differentiable 3D affine transformations. ParamCrop is trained simultaneously with the video backbone using an adversarial objective and learns an optimal cropping strategy from the data. The visualizations show that ParamCrop adaptively controls the center distance and the IoU between two augmented views, and the learned change in the disparity along the training process is beneficial to learning a strong representation. Extensive ablation studies demonstrate the effectiveness of the proposed ParamCrop on multiple contrastive learning frameworks and video backbones. Copyright © 2021, The Authors. All rights reserved.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Adaptive PromptNet for Auxiliary Glioma Diagnosis Without Contrast-Enhanced MRI

Adaptive PromptNet for Auxiliary Glioma Diagnosis Without Co...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yeqi Wang Weijian Huang Cheng Li Xiawu Zheng Yusong Lin Shanshan Wang School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Peng Cheng Laboratory Shenzhen China School of Cyber Science and Engineering Zhengzhou University Zhengzhou China Collaborative Innovation Center for Internet Healthcare Zhengzhou University Zhengzhou China Hanwei IoT Institute Zhengzhou University Zhengzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong China

Multi-contrast magnetic resonance imaging (MRI)-based automatic auxiliary glioma diagnosis plays an important role in the clinic. Contrast-enhanced MRI sequences (e.g., contrast-enhanced T1-weighted imaging) were utilized in most of the existing relevant studies, in which remarkable diagnosis results have been reported. Nevertheless, acquiring contrast-enhanced MRI data is sometimes not feasible due to the patient’s physiological limitations. Furthermore, it is more time-consuming and costly to collect contrast-enhanced MRI data in the clinic. In this paper, we propose an adaptive PromptNet to address these issues. Specifically, a PromptNet for glioma grading utilizing only non-enhanced MRI data has been constructed. PromptNet receives constraints from features of contrast-enhanced MR data during training through a designed prompt loss. To further boost the performance, an adaptive strategy is designed to dynamically weight the prompt loss in a sample-based manner. As a result, PromptNet is capable of dealing with more difficult samples. The effectiveness of our method is evaluated on a widely-used BraTS2020 dataset, and competitive glioma grading performance on NE-MRI data is achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient meta neural heuristic for multi-objective combinatorial optimization 23

Efficient meta neural heuristic for multi-objective combinat...

引用

Proceedings of the 37th International Conference on Neural Information processing Systems

作者： Jinbiao Chen Jiahai Wang Zizhen Zhang Zhiguang Cao Te Ye Siyuan Chen School of Computer Science and Engineering Sun Yat-sen University P.R. China School of Computer Science and Engineering Sun Yat-sen University P.R. China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University P.R. China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China School of Computing and Information Systems Singapore Management University Singapore

Recently, neural heuristics based on deep reinforcement learning have exhibited promise in solving multi-objective combinatorial optimization problems (MOCOPs). However, they are still struggling to achieve high learning efficiency and solution quality. To tackle this issue, we propose an efficient meta neural heuristic (EMNH), in which a meta-model is first trained and then fine-tuned with a few steps to solve corresponding single-objective subproblems. Specifically, for the training process, a (partial) architecture-shared multi-task model is leveraged to achieve parallel learning for the meta-model, so as to speed up the training; meanwhile, a scaled symmetric sampling method with respect to the weight vectors is designed to stabilize the training. For the fine-tuning process, an efficient hierarchical method is proposed to systematically tackle all the subproblems. Experimental results on the multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multi-objective knapsack problem (MOKP) show that, EMNH is able to outperform the state-of-the-art neural heuristics in terms of solution quality and learning efficiency, and yield competitive solutions to the strong traditional heuristics while consuming much shorter time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decoupled and memory-reinforced networks: Towards effective feature learning for one-step person search

arXiv

引用

arXiv 2021年

作者： Han, Chuchu Zheng, Zhedong Gao, Changxin Sang, Nong Yang, Yi Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China ReLER University of Technology Sydney Australia Baidu Research China

The goal of person search is to localize and match query persons from scene images. For high efficiency, one-step methods have been developed to jointly handle the pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. One is the mutual interference between the optimization objectives of multiple sub-tasks. The other is the sub-optimal identification feature learning caused by small batch size when end-to-end training. To overcome these problems, we propose a decoupled and memory-reinforced network (DMRNet). Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework. Further, we build a memory-reinforced mechanism to boost the identification feature learning. By queuing the identification features of recently accessed instances into a memory bank, the mechanism augments the similarity pair construction for pairwise metric learning. For better encoding consistency of the stored features, a slow-moving average of the network is applied for extracting these features. In this way, the dual networks reinforce each other and converge to robust solution states. Experimentally, the proposed method obtains 93.2% and 46.9% mAP on CUHK-SYSU and PRW datasets, which exceeds all the existing one-step methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization

arXiv

引用

arXiv 2022年

作者： Qiu, Zexuan Su, Qinliang Yu, Jianxing Si, Shijing School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangzhou China School of Economics and Finance Shanghai International Studies University China

Efficient document retrieval heavily relies on the technique of semantic hashing, which learns a binary code for every document and employs Hamming distance to evaluate document distances. However, existing semantic hashing methods are mostly established on outdated TFIDF features, which obviously do not contain lots of important semantic information about documents. Furthermore, the Hamming distance can only be equal to one of several integer values, significantly limiting its representational ability for document distances. To address these issues, in this paper, we propose to leverage BERT embeddings to perform efficient retrieval based on the product quantization technique, which will assign for every document a real-valued codeword from the codebook, instead of a binary code as in semantic hashing. Specifically, we first transform the original BERT embeddings via a learnable mapping and feed the transformed embedding into a probabilistic product quantization module to output the assigned codeword. The refining and quantizing modules can be optimized in an end-to-end manner by minimizing the probabilistic contrastive loss. A mutual information maximization based method is further proposed to improve the representativeness of codewords, so that documents can be quantized more accurately. Extensive experiments conducted on three benchmarks demonstrate that our proposed method significantly outperforms current state-of-the-art baselines. Copyright © 2022, The Authors. All rights reserved.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians 16th

Do Not Disturb Me: Person Re-identification Under the Interf...

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Zhao, Shizhen Gao, Changxin Zhang, Jun Cheng, Hao Han, Chuchu Jiang, Xinyang Guo, Xiaowei Zheng, Wei-Shi Sang, Nong Sun, Xing Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab Shanghai China Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783030585389

In the conventional person Re-ID setting, it is assumed that cropped images are the person images within the bounding box for each individual. However, in a crowded scene, off-shelf-detectors may generate bounding boxes involving multiple people, where the large proportion of background pedestrians or human occlusion exists. The representation extracted from such cropped images, which contain both the target and the interference pedestrians, might include distractive information. This will lead to wrong retrieval results. To address this problem, this paper presents a novel deep network termed Pedestrian-Interference Suppression Network (PISNet). PISNet leverages a Query-Guided Attention Block (QGAB) to enhance the feature of the target in the gallery, under the guidance of the query. Furthermore, the involving Guidance Reversed Attention Module and the Multi-Person Separation Loss promote QGAB to suppress the interference of other pedestrians. Our method is evaluated on two new pedestrian-interference datasets and the results show that the proposed method performs favorably against existing Re-ID methods. © 2020, Springer Nature Switzerland AG.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Fully Circuit Implementation of a two-layer Memristive Neural Network for Pattern Recognition

Fully Circuit Implementation of a two-layer Memristive Neura...

引用

International Conference on Information Science and Technology (ICIST)

作者： Mian Li Xiaoping Wang Zhanfei Chen School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665412667;9781665429412

In this paper, a fully circuit implementation of Memristive Neural Network (MNN) is proposed. The forward calculation of the network is based on winner-take-all (WTA) mechanism. The weight updating is achieved through the difference of pre-spike and post-spike, which is more close to the biological weight adjustment mechanism. The network is implemented in a full circuit without additional control units. The designed circuit consists of four modules. The memristive crossbar array module with one-memristor (1M) unit structure can effectively calculate the vector-matrix multiplication with only one step. The switch S is replaced by the transistor in the designed leaky-integrate-and-fire (LIF) module, which can control the integration and leakage of the membrane voltage and realize the lateral inhibition between output neurons. Connecting the integrated monostable trigger and the difference circuit, the post-spike generating module can output the required post-spike. The signal switch module realizes the switching of signals connected to memristors by using voltage-controlled switches. The combination of two modules validly realizes weight updating. The functions of four modules are verified separately. We performed a simulation experiment of 5×3 pixels image classification based on the designed circuit in PSPICE. The circuit output results and the high classification accuracy prove the circuit can be effectively applied in pattern recognition. The noise experiment shows the robustness of the designed circuit.

关键词： Training Neurons Switches Robustness Pattern recognition Integrated circuit modeling Task analysis

来源：评论

学校读者我要写书评

暂无评论

MMTrans-MT: A Framework for Multimodal Emotion Recognition Using Multitask Learning

MMTrans-MT: A Framework for Multimodal Emotion Recognition U...

引用

International Workshop on Advanced Computational intelligence (IWACI)

作者： Jinrui Shen Jiahao Zheng Xiaoping Wang the School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China the School of Artificial Intelligence and Automation the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

With the development of deep learning, emotion recognition tasks are more inclined to use multimodal data and adequate supervised information to improve accuracy. In this work, MMTrans-MT (Multimodal Transformer-Multitask), the framework for multimodal emotion recognition using multitask learning is proposed. It has three modules: modalities representation module, multimodal fusion module, and multitask output module. Three modalities, i.e, words, audio and video, are comprehensively utilized to carry out emotion recognition by a simple but efficient fusion model based on Transformer. As for multitask learning, the two tasks are defined as categorical emotion classification and dimensional emotion regression. Considering a potential mapping relationship between two kinds of emotion model, multitask learning is adopted to make the two tasks promote each other and improve recognition accuracy. We conduct experiments on CMU-MOSEI and IEMOCAP datasets. Comprehensive experiments show that the accuracy of recognition using multimodal information is higher than that using unimodal information. Adopting multitask learning promotes the performance of emotion recognition.

关键词： Learning systems Deep learning Emotion recognition Correlation Computational modeling Task analysis Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Tight Formulations of Unit Commitment with General Start-Up Ramp Rate Constraints

Tight Formulations of Unit Commitment with General Start-Up ...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Yijie Gao Xuan Zhang Yaowen Yu Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Hitachi ABB Power Grid San Jose California US

ISBN: (纸本)9781665414401

Unit commitment (UC) is a central market clearing process in wholesale electricity markets. With the increasing size and complexity of market-clearing models, UC problems become more and more complicated. To improve the computation efficiency, this paper tightens UC formulations with the general start-up ramp rate. Through analyzing their parameters over three periods, units are categorized into several categories for constructing corresponding tight formulations, and three of the categories are beyond existing works. By applying a recent systematic formulation tightening approach on top of these categories, new tight constraints of the general start-up ramp rate have been obtained. Numeral testing results illustrate the tightening process and demonstrate the improvement of computational efficiency when using our tightened formulations.

关键词： Systematics Computational modeling Conferences Electricity supply industry Computational efficiency Complexity theory Testing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning of the Kansas City Cardiomyopathy Questionnaire for Predicting Sudden Cardiac Death in Heart Failure with Preserved Ejection Fraction (HFpEF): KCCQ-SCD Score

SSRN

引用

SSRN 2023年

作者： Liu, Xiao Zhang, Zenghui Pan, Hong Abudukeremu, Ayiguli Zhao, Ke Wang, Yue He, Wanbing Cao, Zhengyu Wu, Maoxiong Chen, Zhiteng Zhang, Minghai Yan, Zhiwei Gao, Qingyuan Zhu, Wengen Zhang, Haifeng Jiang, Yuan Liu, Zhaoyu Zhang, Yuling Chen, Yangxin Wang, Jingfeng Department of Cardiology Sun Yat-sen Memorial Hospital of Sun Yat-sen University Guangdong Province Guangzhou China Guangdong Province Key Laboratory of Arrhythmia and Electrophysiology Guangdong Province Guangzhou China Guangzhou Key Laboratory of Molecular Mechanism and Translation in Major Cardiovascular Disease Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation Guangdong-Hong Kong Joint Laboratory for RNA Medicine Sun Yat-Sen Memorial Hospital Sun Yat-Sen University Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Department of Cardiology Department of Cardiology The first Affiliated Hospital of Sun Yat-sen University Guangdong Province Guangzhou China

Background: Sudden cardiac death (SCD) is the leading cause of death in in heart failure with preserved ejection fraction (HFpEF). The predictive value of Kansas City Cardiomyopathy Questionnaire (KCCQ) score on SCD remained ***: This study aimed to develop and validate a predictive model for SCD risk stratification in HFpEF based on the KCCQ score, age, and ***: We developed machine learning models (logistic regression, logistic regression with lasso regression, random forest, gradient descent boosting, and K-Nearest Neighbors) to predict SCD risk in HFpEF, using age, sex, and KCCQ score from Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist trial (TOPCAT). Model performance was evaluated by C statistics and decision curves. Results: Of 3,445 patients (mean age 69.1 years), 48.5% were male. During a mean follow-up period of 3.37 years, 111 patients died of SCD. The models were trained on 2,756 patients and validated on the remaining 689 patients. The lasso model demonstrated superior performance, with C statistics of 0.69 and a Brier score of 0.03. A total of 304 patients were categorized as high risk by this prediction model in validation set. The estimated 5-year cumulative incidence of SCD was 9.6% compared with 2.0% in those with low risk of SCD. Decision curve analysis indicated greater net benefit for the KCCQ-SCD score across various clinical ***: KCCQ-based machine learning model for SCD risk assessment in HFpEF presents a promising alternative, providing valuable prognostic information in a more accessible and patient-centric *** Registration: URL: https://***. Unique identifier: ***: This work was supported by grants from National Natural Science Foundation of China (82070237, 82270254, 82271609, 81970200, 82100369, 82170492), and Guangzhou Science and Technology Plan Project (2023B01J1011). Natural Science Foundation of Guangdong Province

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：