检索结果-内蒙古大学图书馆

A Multi-scale Network for Semantic Segmentation of 3D Point Clouds

学校读者我要写书评

暂无评论

A Multi-scale Network for Semantic Segmentation of 3D Point ...

Chinese Automation Congress (CAC)

作者： Ying He Li Xiao Yong Jiang Zhigang Sun Zhuo Wang Gang Peng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

Semantic segmentation is a fundamental operation in scene analysis. In this paper, an effective multiscale network for 3D point cloud semantic segmentation was introduced. By using a multiscale local feature extraction module which composed of four feature extractors of different scales in parallel, the generalizability of network for complex structures is enhanced effectively. To adaptively learn important feature channels, an attention mechanism is designed. Combining multiple features through skip connection, the network can preferably assign the semantic label for every point by exploiting global and local features. Experiments on 3D dataset (S3DIS) verify that our network is able to learn local region features, and the results are superior or comparable to the state-of-the-art.

关键词： Feature extraction Three-dimensional displays Semantics Two dimensional displays Intelligent control image processing Automation

A memristor-based generalization and differentiation circuit design and the application in recognition

学校读者我要写书评

暂无评论

A memristor-based generalization and differentiation circuit...

第三十九届中国控制会议

作者： Meijia Shang Xiaoping Wang Mian Li the School of Artificial Intelligence and Automation Huazhong University of Science and Technology IEEE the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China

The traditional Pavlov associative memory circuit realizes the law of learning and forgetting in classical conditioned reflex. In addition, the law of generalization and differentiation also belongs to classical conditioned reflex, so the process of associative memory can be more effectively simulated by adding generalization and differentiation theory on the basis of traditional associative memory. In this paper, a memristor-based circuit is designed to implement generalization and differentiation based on Pavlov associative memory. The circuit can be applied to simple classification recognition. Based on the features of objects as input, the output of the circuit is used as the classification result to achieve the function of classification and recognition. Finally,the accuracy of classification recognition on the generalization and differentiation circuit proposed in this paper can be verified by the simulation results in PSPICE.

关键词： Memristor generalization differentiation Pavlov associative memory recognition

Graph-based scale-aware network for human parsing 1

学校读者我要写书评

暂无评论

2nd Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2019

作者： Yang, Beibei Yu, Changqian Liu, Jiahui Gao, Changxin Sang, Nong Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9783030317232

ISBN: (纸本)9783030317225

Recent work has made considerable progress in exploring contextual information for human parsing with the Fully Convolutional Network framework. However, there still exist two challenges: (1) inherent relative relationships between parts;(2) scale variation of human parts. To tackle both problems, we propose a Graph-Based Scale-Aware Network for human parsing. First, we embed a Graph-Based Part Reasoning Layer into the backbone network to reason the relative relationship between human parts. Then we construct a Scale-Aware Context Embedding Layer, which consists of two branches to capture scale-specific contextual information, with different receptive fields and scale-specific supervisions. In addition, we adopt an edge supervision to further improve the performance. Extensive experimental evaluations demonstrate that the proposed model performs favorably against the state-of-the-art human parsing methods. More specifically, our algorithm achieves 53.32% (mIoU) on the LIP dataset. © Springer Nature Switzerland AG 2019.

关键词： Embeddings

Integrating Informativeness, Representativeness and Diversity in Pool-Based Sequential Active Learning for Regression

学校读者我要写书评

暂无评论

Integrating Informativeness, Representativeness and Diversit...

International Joint Conference on Neural Networks (IJCNN)

作者： Ziang Liu Dongrui Wu Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approach for reducing this data labeling effort. It optimally selects the best few samples to label, so that a better machine learning model can be trained from the same number of labeled samples. This paper considers active learning for regression (ALR) problems. Three essential criteria - informativeness, representativeness, and diversity - have been proposed for ALR. However, very few approaches in the literature have considered all three of them simultaneously. We propose three new ALR approaches, with different strategies for integrating the three criteria. Extensive experiments on 12 datasets in various domains demonstrated their effectiveness.

关键词： Computational modeling Clustering algorithms Machine learning Training Labeling Predictive models image processing

Towards explainable multi-party learning: A contrastive knowledge sharing framework

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gao, Yuan Li, Jiawei Gong, Maoguo Xie, Yu Qin, A.K. The School of Electronic Engineering Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xidian University Shaanxi Province Xi'an710071 China The Key Laboratory of Computational Intelligence Chinese Information Processing Ministry of Education Shanxi University Taiyuan030006 China The department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia

Multi-party learning provides solutions for training joint models with decentralized data under legal and practical constraints. However, traditional multi-party learning approaches are confronted with obstacles such as system heterogeneity, statistical heterogeneity, and incentive design. How to deal with these challenges and further improve the efficiency and performance of multi-party learning has become an urgent problem to be solved. In this paper, we propose a novel contrastive multi-party learning framework for knowledge refinement and sharing with an accountable incentive mechanism. Since the existing parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogize multiparty learning as a many-to-one knowledge sharing problem. The approach is capable of integrating the acquired explicit knowledge of each client in a transparent manner without privacy disclosure, and it reduces the dependence on data distribution and communication environments. The proposed scheme achieves significant improvement in model performance in a variety of scenarios, as we demonstrated through experiments on several real-world datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge management

REST: Relational event-driven stock trend forecasting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Wentao Liu, Weiqing Xu, Chang Bian, Jiang Yin, Jian Liu, Tie-Yan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Microsoft Research Asia Beijing China School of Artificial Intelligence Sun Yat-sen University Zhuhai China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Stock trend forecasting, aiming at predicting the stock future trends, is crucial for investors to seek maximized profits from the stock market. Many event-driven methods utilized the events extracted from news, social media, and discussion board to forecast the stock trend in recent years. However, existing event-driven methods have two main shortcomings: 1) overlooking the influence of event information differentiated by the stock-dependent properties;2) neglecting the effect of event information from other related stocks. In this paper, we propose a relational event-driven stock trend forecasting (REST) framework, which can address the shortcoming of existing methods. To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts. To address the second shortcoming, we construct a stock graph and design a new propagation layer to propagate the effect of event information from related stocks. The experimental studies on the real-world data demonstrate the efficiency of our REST framework. The results of investment simulation show that our framework can achieve a higher return of investment than baselines. © 2021, CC BY.

关键词： Forecasting

Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Lei Zhang, Yuzhong Zhang, Jiadong Qian, Xuejun Gong, Chen Sun, Kun Ding, Zhongxiang Wang, Xing Li, Zhenhui Liu, Zaiyi Shen, Dinggang The School of Health Science and Engineering University of Shanghai for Science and Technology Shanghai China The School of Biomedical Engineering ShanghaiTech University China The School of Computer Science and Engineering Nanjing University of Science and Technology China Ruijin Hospital Shanghai Jiaotong University School of Medicine China Department of Radiology Key Laboratory of Clinical Cancer Pharmacology and Toxicology Research of Zhejiang Province China The Shanghai General Hospital Shanghai JiaoTong University China Department of Radiology The Third Affiliated Hospital of Kunming Medical University China Department of Radiology Guangdong Provincial Peo-ple's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China School of Biomedical Engineering State Key Laboratory of Advanced Medical Materials and Devices ShanghaiTech University Shanghai201210 China Shanghai United Imaging Intelligence Co. Ltd. Shanghai200232 China Shanghai Clinical Research and Trial Center Shanghai201210 China

Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However, accurate segmentation of breast tumor is a challenging task, often necessitating the development of complex networks. To strike an optimal tradeoff between computational costs and segmentation performance, we propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. Specifically, the hybrid network consists of a encoder-decoder architecture by stacking convolution and deconvolution layers. Effective 3D transformer layers are then implemented after the encoder subnetworks, to capture global dependencies between the bottleneck features. To improve the efficiency of hybrid network, two parallel encoder subnetworks are designed for the decoder and the transformer layers, respectively. To further enhance the discriminative capability of hybrid network, a prototype learning guided prediction module is proposed, where the category-specified prototypical features are calculated through online clustering. All learned prototypical features are finally combined with the features from decoder for tumor mask prediction. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network achieves superior performance than the state-of-the-art (SOTA) methods, while maintaining balance between segmentation accuracy and computation cost. Moreover, we demonstrate that automatically generated tumor masks can be effectively applied to identify HER2-positive subtype from HER2-negative subtype with the similar accuracy to the analysis based on manual tumor segmentation. The source code is available at https://***/ZhouLlab/PLHN. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Zhiping Xu, Wentao Liu, Weiqing Bian, Jiang Yin, Jian Liu, Tie-Yan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Microsoft Research Asia Beijing China School of Artificial Intelligence Sun Yat-sen University Zhuhai China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China

Learning the embeddings of knowledge graphs (KG) is vital in artificial intelligence, and can benefit various downstream applications, such as recommendation and question answering. In recent years, many research efforts have been proposed for knowledge graph embedding (KGE). However, most previous KGE methods ignore the semantic similarity between the related entities and entity-relation couples in different triples since they separately optimize each triple with the scoring function. To address this problem, we propose a simple yet efficient contrastive learning framework for tensor decomposition based (TDB) KGE, which can shorten the semantic distance of the related entities and entity-relation couples in different triples and thus improve the performance of KGE. We evaluate our proposed method on three standard KGE datasets: WN18RR, FB15k-237 and YAGO3-10. Our method can yield some new state-of-the-art results, achieving 51.2% MRR, 46.8% Hits@1 on the WN18RR dataset, 37.8% MRR, 28.6% Hits@1 on FB15k-237 dataset, and 59.1% MRR, 51.8% Hits@1 on the YAGO3-10 dataset. © 2021, CC BY.

关键词： Knowledge graph

Reliability on Deep Learning Models: A Comprehensive Observation

学校读者我要写书评

暂无评论

Reliability on Deep Learning Models: A Comprehensive Observa...

International Symposium on System and Software Reliability (ISSSR)

作者： Yuhong Zhang Chunjing Xiao School of Artificial Intelligence and Big Data Key Laboratory of Grain Information Processing and Control Ministry of Education Henan University of Technology Zhengzhou China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (数字)9780738104973

ISBN: (纸本)9781665423236

This paper provides a comprehensive observation to examine the reliability of deep learning (DL) models. First, we will briefly introduce the essential background and kernel techniques in deep learning, such as downsampling and nonlinear discontinuity. Each of them may have some relation to the reliability of DL models. Then we discuss the inherent structural flaws of deep learning and the risk of unreliability that can result from it. Subsequently, we discuss various ways of generating adversarial samples that affect the DL model's reliability and corresponding preventive measures. Finally, we complete this observation by identifying current challenges and future trends for research.

关键词： Reliability Deep learning Biological neural networks Perturbation methods Neural networks Feature extraction Data models