检索结果-内蒙古大学图书馆

27th IEEE International Conference on parallel and Distributed Systems, ICPADS 2021

作者： Li, Kun Wang, Nan Liu, Xinyu School of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781665408783

In recommender systems, due to the lack of explicit feedback features, datasets with implicit feedback are always accustomed to train all samples without separating them during model training, without considering the non-consistency of samples. This leads to a significant decrease in sample utilization and creates challenges for model training. Also, little work has been done to explore the intrinsic laws implied in the implicit feedback dataset and how to effectively train the implicit feedback data. In this paper, we first summarize the variation pattern of loss with model training for different rating samples in the explicit feedback dataset, and find that model training is highly sensitive to the ratings. Second, we design an adaptive hierarchical training function with dynamic thresholds that can effectively distinguish different rating samples in the dataset, thus optimizing the implicit feedback dataset into an explicit feedback dataset to some extent. Finally, to better learn samples with different ratings, we also propose an adaptive hierarchical training strategy to obtain better training results in the implicit feedback dataset. Extensive experiments on three datasets show that our approach achieves excellent performance and greatly improves the performance of the model. © 2021 IEEE.

关键词： adaptive hierarchical training implicit feedback sample utilization sensitive

来源：评论

学校读者我要写书评

暂无评论

FasterBERT with Double Loss Function Based on Batch Data Preprocessing 2

FasterBERT with Double Loss Function Based on Batch Data Pre...

引用

2nd International Conference on Electronics, Communications and Information Technology, CECIT 2021

作者： Duan, Pengqi Zheng, Yudong Lu, Jun College of Computer Science and Technology Heilongjiang University HLJU Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781665437578

Even though pre-trained language models like BERT and XLNet have produced significant consequences on a variety of tasks of natural language processing, they are difficult to deploy in practical applications due to their large number of parameters, and huge calculation and memory costs. In order to improve the training speed and inference speed of the pre-trained model, the FasterBERT model is proposed in this paper. This model combines batch data preprocessing method with knowledge distillation. It increases the model to increase the model speed and maintains the original accuracy. Furthermore, double loss function is incorporated during the knowledge distillation process in this paper, so that the model can better learn the knowledge of the teacher model and the knowledge of the real labels. The accuracy of the model is improved. The effectiveness of the FasterBERT model is demonstrated on 12 datasets in this paper. Training speed of the FasterBERT is 1.1-2.2 times higher than FastBERT and 2-43 times higher than BERT. In addition, the accuracy is up to 0.6% higher than that of FastBERT, and the accuracy is better than that of the BERT model on three datasets. The experiments show that the FasterBERT model proposed in this paper performs well on six Chinese datasets and six English datasets. The speed is greatly improved while the accuracy of the task also has a significant effect. © 2021 IEEE.

关键词： Speed

来源：评论

学校读者我要写书评

暂无评论

A Weakly Supervised Semantic Segmentation Model with Enhanced CLIP Feature Extraction

A Weakly Supervised Semantic Segmentation Model with Enhance...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fanxuan Kong Jun Lu College of Computer Science and Technology Heilongjiang University Harbin China Jiaxiang Industrial Technology Research Institute of Heilongjiang University Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper addresses the limitations of the Contrastive Language-Image Pre-training (CLIP) model’s image encoder and proposes a segmentation model WSSS-ECFE with enhanced CLIP feature extraction, aiming to improve the performance of the Weakly Supervised Semantic Segmentation (WSSS) task. WSSS-ECFE employs the Enhanced Bottleneck module proposed in this paper and adds dynamic residual connection to improve the model’s processing effect on complex scenes. In terms of implementation, the Enhanced Bottleneck module employs the Swish activation function and the Depthwise Separable Convolution to enhance the feature extraction and segmentation capability of the model, and uses multiple attention mechanisms to further optimize the feature representation and segmentation accuracy. The WSSS task on the public datasets PASCAL VOC 2012 and MS COCO 2014 achieves 82.6% and 56.3% mean intersection over union (mIoU), achieving state-of-the-art performance in models with low resource requirements.

关键词： Training Attention mechanisms Accuracy Convolution Semantic segmentation Graphics processing units Feature extraction Boosting Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

引用

11th International Conference on Information Science and Technology, ICIST 2021

作者： Wang, Zhongqing Yang, Yan Zhong, Yingli Heilongjiang University School of Computer Science Technology Harbin China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781665412667

Graph similarity search is an important research problem in many applications, such as finding result graphs that have a similar structure to a given entity in biochemistry, data mining, and pattern recognition. Top-k graph similarity search is one of graph similarity search tasks, which aims to find the top-k graphs that are most similar to the query graph in a given graph database. In this paper, the top-k similarity search problem based on the graph edit distance is studied according to the corollary of the partitioned similarity theorem. Firstly, in order to speed up the online search process and avoid scanning each graph in the database one by one, an offline hierarchical inverted index is constructed to satisfy top-k search. Secondly, the offline hierarchical inverted index is used to filter the candidate graphs online and verify them, which reduces the time of searching the graphs. Finally, the good performance of the algorithm in running time and scalability is verified by running the similarity algorithm on real dataset and synthetic dataset. © 2021 IEEE.

关键词： Graph databases

来源：评论

学校读者我要写书评

暂无评论

Visible-Infrared Image Fusion Based on Double- Density Wavelet and Thermal Exchange Optimization 5

Visible-Infrared Image Fusion Based on Double- Density Wavel...

引用

5th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Guo, Hao Chen, Jingyu Yang, Xuan Jiao, Qingliang Liu, Ming Beijing Institute of Environmental Features Beijing China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

Infrared and visible image fusion has been a hot issue in image fusion. However, the parameters and result image have many proposed. In this paper, a novel visible infrared image fusion algorithm based on double-density wavelet and thermal exchange optimization is proposed. The pre-processed infrared and visible images are decomposed into detail layers and background layers by double-density wavelet transform. Thermal exchange optimization is used to estimate the number of layers and weight thresholds of decomposition. Experimental shows that both visual effects and quantitative analysis of proposed algorithm can get the best results. © 2021 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Community Search in Spatial Uncertain Network

Community Search in Spatial Uncertain Network

引用

2021 Asia-Pacific Conference on Image Processing, Electronics and Computers, IPEC 2021

作者： Zhang, Wenqian Zhong, Yingli Yang, Yan School of Computer Science Technology Heilongjiang University Harbin150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin150080 China

Community search is to explore valuable target community structure from a large social network. In real community, every point has a geographic location information, and many edges are uncertain. Such a network is called spatial uncertain network. In order to meet the existing needs, this paper studies the community search in the spatial uncertain network so that the searched communities can be relatively close in the geographical location and the relationship between each other is also very close. Based on the spatial uncertain graph, this paper proposes K-R-τ community, and proposes a linear algorithm and a two-dimensional algorithm for community search in the spatial uncertain network. A large number of experiments are carried out on several real datasets, and the results show that the algorithm proposed in this paper is effective and accurate. © Published under licence by IOP Publishing Ltd.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Cross-Modality Encoder Representations Based On External Attention Mechanism

Cross-Modality Encoder Representations Based On External Att...

引用

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Yudong Zheng Jun Lu College of Computer Science and Technology Heilongjiang University Harbin China College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

With the prevalence of deep learning, people use multi-modality information for interpretation and reasoning. In this paper, a cross-modality encoder CMEEA (cross-modality encoder representation based on external attention mechanism) is adopted to improve the accuracy of the model. The two external storage units of CMEEA can be regarded as a dictionary of the whole dataset to improve the performance of the network, while learning more representative features of the input and reducing the computational cost. This paper uses five pretraining tasks that help the model learn internal modal and cross-modal relationships. It also verifies the generalizability of the model by applying the pretraining cross-modal model to the visual inference task NLVR 2 , and improves the previous results by 0.1%. By fine-tuning the pretrain parameters, the model improves by 1.3% on visual question answering (VQA).

关键词： Training Deep learning Analytical models Visualization Dictionaries Computational modeling Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

A New Feature Fusion Method Based on Pre-Training Model for Sequence Labeling

A New Feature Fusion Method Based on Pre-Training Model for ...

引用

International Conference on Data Storage and Data Engineering (DSDE)

作者： Shichuan Yu Yan Yang School of computer science and technology Heilongjiang University Harbin China Heilongjiang Key Laboratory of Database and Parallel Computing Heilongjiang University Harbin China

To fuse vocabulary features into the pre-training model is the mainstream data feature processing method for sequence labelling tasks. In general, the feature fusion methods that have been proposed at present are direct fusion outside the pre-training model or fusion of lexical features using attention mechanism. However, the study found that this way of vocabulary enhancement does not conform to the word formation rules of modern Chinese. In the Chinese language, it is easy to fuse irrelevant or even incorrect lexical features into the sequence using the above feature processing methods, which is bad for the experimental results of the Chinese sequence labelling task. To solve these problems, we propose to use Cosine Similarity Adapter to process lexical features in Chinese sequence labelling tasks. CSBERT is a hybrid model using this structure based on BERT, which conforms to the word formation rules of modern Chinese to a certain extent. It can fuse the features of the word into the character or eliminate the features of the word in the character according to the cosine similarity between the character vector and a word vector. The experimental results show that CSBERT has better ability to label Chinese sequences than the benchmark model. CSBERT has achieved the best experimental results such as F1-Score on 7 open datasets and the best ability of multi-label classification, which proves that the model has good practical value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DMSA: DYNAMIC MULTI-SCALE UNSUPERVISED SEMANTIC SEGMENTATION BASED ON ADAPTIVE AFFINITY

arXiv

引用

arXiv 2023年

作者： Yang, Kun Lu, Jun College of Computer Science and Technology Heilongjiang University 150080 Harbin China Jiaxiang Industrial Technology Research Institute of HLJU Jining Shandong Province China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At the same time, a dynamic dilation strategy is designed to better capture multi-scale context information. Secondly, a Pixel-Adaptive Refinement (PAR) module is introduced, which can adaptively refine the initial pseudo labels after feature fusion to obtain high quality pseudo labels. Experiments show that the proposed DSMA framework is superior to the existing methods on the saliency dataset. On the COCO 80 dataset, the MIoU is improved by 2.0, and the accuracy is improved by 5.39. On the Pascal VOC 2012 Augmented dataset, the MIoU is improved by 4.9, and the accuracy is improved by 3.4. In addition, the convergence speed of the model is also greatly improved after the introduction of the PAR module. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation Based On Adaptive Affinity

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kun Yang Jun Lu College of Computer Science and Technology Heilongjiang University Harbin China Jiaxiang Industrial Technology Research Institute of HLJU Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

关键词： Training Representation learning Adaptation models Semantic segmentation Semantics Signal processing Transformers

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：