2021 International Joint Conference on Neural Networks (IJCNN)最新文献_第10页

Study of XAI-capabilities for early diagnosis of plant drought xai在植物干旱早期诊断中的应用研究

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534105

Irina E. Maximova, E. Vasiliev, A. Getmanskaya, Dmitry Kior, V. Sukhov, V. Vodeneev, V. Turlapov

{"title":"Study of XAI-capabilities for early diagnosis of plant drought","authors":"Irina E. Maximova, E. Vasiliev, A. Getmanskaya, Dmitry Kior, V. Sukhov, V. Vodeneev, V. Turlapov","doi":"10.1109/IJCNN52387.2021.9534105","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534105","url":null,"abstract":"The Single Layer Perceptron (SLP) has been studied as an Explainable Artificial Intelligence (XAI) Interactive Unit. On the basis of SLP(N), with an arbitrary number N of neurons on the hidden layer, two models were built: classification and regression. To achieve interactivity, the training on images is replaced by training on its feature vectors. The feature vector includes the results of image processing in three different ways, forming 3 feature groups: STAT {mean, std, min, max}; HIST - values of the quantized histogram; GLCM (gray-level co-occurrence matrix) - textural features. To give XAI properties to the models, they are equipped with tools for analyzing and visualizing the weight and efficiency of the components of the feature vector. It is also possible to optimize the classifier and regressor by the number of neurons, features, and quantization levels (histogram bins and gray levels for GLCM). The study was carried out on the example of the problem of early diagnosis of drought stress in wheat plants, recorded by sensors of two different types: Thermal IR (TIR) and RGB. The problems of stress classification and prediction (regression) of the duration of a plant being under stress are solved. The SLP classifier and the SLP regressor are also used as tools for analyzing the stress features efficiency. Two groups of grayscale NDVI (normalized difference vegetation index) images were used as source data: TIR-based; RGB-based. Replacing source images onto their feature vectors gave to reduce the training time of the models to a fraction of a second. The weights and the influence of drought stress features on the efficiency of classification and regression for both types of source images were shown, and SLP models were optimized. Software tools: pytorch, scikit-image, scikit-learn.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126555916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Low-Resource Neural Machine Translation with Neural Episodic Control 基于神经情景控制的低资源神经机器翻译

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533677

Nier Wu, H. Hou, Shuo Sun, Wei Zheng

引用次数: 0

An efficient lightweight deep neural network for real-time object 6D pose estimation with RGB-D inputs 基于RGB-D输入的实时目标6D姿态估计的高效轻量级深度神经网络

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534175

Yuzhou Liang, Fan Chen, Guoyuan Liang, Xinyu Wu, Wei Feng

{"title":"An efficient lightweight deep neural network for real-time object 6D pose estimation with RGB-D inputs","authors":"Yuzhou Liang, Fan Chen, Guoyuan Liang, Xinyu Wu, Wei Feng","doi":"10.1109/IJCNN52387.2021.9534175","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534175","url":null,"abstract":"6D pose estimation for objects is an important technology in human-computer interaction. Previous works trained one or more complicated networks to predict 6D poses. Although complex models have nice performance generally, the high storage and computation cost make it difficult to be applied on hardware platforms with limited computing ability such as the low-cost mobile terminal. Hence, how to reduce the complexity of the model while maintaining accuracy remains a challenge. In this paper, we present a lightweight generic architect that processes the color and depth images respectively by employing two efficient backbone networks, then use a fusion network to realize pose regression. Furthermore, an iterative refinement network compressed is implemented by using the Filter Pruning via Geometric Median (FPGM) algorithm to refine the poses while improving real-time performance. Comprehensive experiments conducted on two benchmark datasets, LineMOD and YCB-Video, confirm that the proposed model is more than twice as fast as the state-of-the-art (SOTA) DenseFusion. For main metrics, the BFLOPs (Billion FLoat OPerations) are reduced by 97.0%, and the parameter size declines by 87.4%. The average distance (ADD) for LineMOD increases by 2.6%. The overall performance of the new model is proven outperforming SOTA methods both in efficiency and accuracy.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117321040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Channel Hourglass Residual Network For Single Image Super-Resolution 单图像超分辨率通道沙漏残差网络

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533568

Fang Hao, Xindi Ma, Taiping Zhang, Yuanyan Tang

引用次数: 0

Deep Content Guidance Network for Arbitrary Style Transfer 面向任意风格迁移的深度内容引导网络

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533953

Dibo Shi, Huang Xie, Yi Ji, Ying Li, Chunping Liu

{"title":"Deep Content Guidance Network for Arbitrary Style Transfer","authors":"Dibo Shi, Huang Xie, Yi Ji, Ying Li, Chunping Liu","doi":"10.1109/IJCNN52387.2021.9533953","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533953","url":null,"abstract":"Arbitrary style transfer refers to generate a new image based on any set of existing images. Meanwhile, the generated image retains the content structure of one and the style pattern of another. In terms of content retention and style transfer, the recent arbitrary style transfer algorithms normally perform well in one, but it is difficult to find a trade-off between the two. In this paper, we propose the Deep Content Guidance Network (DCGN) which is stacked by content guidance (CG) layers. And each CG layer involves one position self-attention (pSA) module, one channel self-attention (cSA) module and one content guidance attention (cGA) module. Specially, the pSA module extracts more effective content information on the spatial layout of content images and the cSA module makes the style representation of style images in the channel dimension richer. And in the non-local view, the cGA module utilizes content information to guide the distribution of style features, which obtains a more detailed style expression. Moreover, we introduce a new permutation loss to generalize feature expression, so as to obtain abundant feature expressions while maintaining content structure. Qualitative and quantitative experiments verify that our approach can transform into better stylized images than the state-of-the-art methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130824652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Wasserstein Distance-Based Domain Adaptation and Its Application to Road Segmentation 基于Wasserstein距离的区域自适应及其在道路分割中的应用

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534121

Seita Kono, Takaya Ueda, Enrique Arriaga-Varela, I. Nishikawa

{"title":"Wasserstein Distance-Based Domain Adaptation and Its Application to Road Segmentation","authors":"Seita Kono, Takaya Ueda, Enrique Arriaga-Varela, I. Nishikawa","doi":"10.1109/IJCNN52387.2021.9534121","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534121","url":null,"abstract":"Domain adaptation is used in applying a classifier acquired in one data domain to another data domain. A classifier obtained by supervised training with labeled data in an original source domain can also be used for classification in a target domain in which the labeled data are difficult to collect with the help of domain adaptation. The most recently proposed domain adaptation methods focus on data distribution in the feature space of a classifier and bring the data distribution of both domains closer through learning. The present work is based on an existing unsupervised domain adaptation method, in which both distributions become closer through adversarial training between a target data encoder to the feature space and a domain discriminator. We propose to use the Wasserstein distance to measure the distance between two distributions, rather than the well-known Jensen-Shannon divergence. Wasserstein distance, or earth mover's distance, measures the length of the shortest path among all possible pairs between a corresponding pair of variables in two distributions. Therefore, minimization of the distance leads to overlap of the corresponding data pair in source and target domain. Thus, the classifier trained in the source domain becomes also effective in the target domain. The proposed method using Wasserstein distance shows higher accuracies in the target domains compared with an original distance in computer experiments on semantic segmentation of map images.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130910625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

TA-GAN: GAN based Traffic Augmentation for Imbalanced Network Traffic Classification 基于GAN的不平衡网络流量分类的流量增强算法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533942

Yu Guo, G. Xiong, Zhen Li, Junzheng Shi, Mingxin Cui, Gaopeng Gou

{"title":"TA-GAN: GAN based Traffic Augmentation for Imbalanced Network Traffic Classification","authors":"Yu Guo, G. Xiong, Zhen Li, Junzheng Shi, Mingxin Cui, Gaopeng Gou","doi":"10.1109/IJCNN52387.2021.9533942","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533942","url":null,"abstract":"As the mainstream in network traffic classification (NTC), machine learning (ML) based methods suffer performance degradation due to the imbalance distribution of Internet traffic. Data augmentation methods including the traditional oversampling techniques and the Generative Adversarial Network (GAN) based generation methods are most commonly used to counter the imbalance problem in NTC. However, the former is prone to overfitting and introducing noise. The latter overcomes the above weaknesses, but the quality of the generated traffic samples is difficult to judge. Besides, these methods all divide the imbalanced traffic classification problem into two subproblems, which cannot guarantee the global optimality. In this paper, we propose a GAN based Traffic Augmentation (TA-GAN) for imbalanced traffic classification. TA-GAN is an end-to-end framework that integrates the generation of the minority traffic samples with the training of the target classifier. We design the feedback mechanism to better guide the direction of the sample generation and simultaneously indicate the quality of the synthesized samples. Moreover, the existing deep learning-based NTC methods can be easily adapted to imbalance scenarios with TA-GAN. Comprehensive experiments on the public ISCXVPN2016 dataset demonstrate that TA-GAN effectively mitigates the influence of traffic imbalance (a maximum 14.64% improvement to the minority class' $F_{1}$ score) and outperforms the state-of-the-art methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Deep Reinforcement Learning Based Cost-Benefit Analysis for Hospital Capacity Planning 基于深度强化学习的医院容量规划成本效益分析

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533482

S. S. Shuvo, Md Rubel Ahmed, H. Symum, Yasin Yılmaz

{"title":"Deep Reinforcement Learning Based Cost-Benefit Analysis for Hospital Capacity Planning","authors":"S. S. Shuvo, Md Rubel Ahmed, H. Symum, Yasin Yılmaz","doi":"10.1109/IJCNN52387.2021.9533482","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533482","url":null,"abstract":"The stochastic nature of hospital bed demands and population growth rate in high migration areas poses significant challenges for the authorities to devise an appropriate hospital augmentation scheme. In this study, we propose a deep reinforcement learning (DRL) based model that can identify an appropriate hospital expansion plan for a particular geographical region of interest. Our proposed model analyzes the cost-benefit over a range of geographic regions and recommends the best capacity expansion area. We consider hospital bed numbers as a capacity determiner and population demographics for analyzing future demands economics in our approach. We divide a concerned geographic region into several sub-regions based on the local administrative body to recommend a sub-region where augmentation is necessary. The RL agent then works based on the age group, population growth, and current bed capacity utilizing the Advantage Actor-Critic (A2C) algorithm to minimize the cumulative cost. We also implemented our proposed approach for a case study in the Tampa Bay region, Florida, USA, to identify a hospital augmentation plan. The results from the case study verify this approach's superiority over traditional per capita-based and complaint-based policies.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133573483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

EACoupledCF: An Enhanced Attention-based Coupled Collaborative Filtering Approach for Recommendation EACoupledCF:一种增强的基于注意力的推荐耦合协同过滤方法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534267

Feng Zhang, Xiangfu Meng, Ruimin Chai, Quangui Zhang

{"title":"EACoupledCF: An Enhanced Attention-based Coupled Collaborative Filtering Approach for Recommendation","authors":"Feng Zhang, Xiangfu Meng, Ruimin Chai, Quangui Zhang","doi":"10.1109/IJCNN52387.2021.9534267","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534267","url":null,"abstract":"Recommender system is the core to solve the problem of information overload. Meanwhile, non-IID (non-Independently Identically Distribution) recommender system shows its potential in improving recommendation quality and solving the problems such as sparsity and cold start. With the development of deep learning, recommendation has become a hot topic and a large number of studies have proved the effectiveness of deep learning in recommender system. In this work, we contribute a new multi-layer neural network framework, EACoupledCF (Enhanced Attention-based Coupled Collaborative Filtering), to perform collaborative filtering. The idea of EACoupledCF is to use an outer product to explicitly model the pairwise correlations between the dimensions of the embedding space, utilize the convolutional neural network and introduce spatial attention mechanism to learn high-order features between embedded dimensions. At the same time, it also proposes a novel model called DCCF (Deep Combination Collaborative Filtering) for implicit feedback learning in order to capture the interactive information better. In contrast to the existing neural recommendation models, the experimental results obtained on two real-word large datasets show the effectiveness of our proposed model.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132583896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Autoencoders Without Reconstruction for Textural Anomaly Detection 纹理异常检测的无重构自编码器

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533804

Philip A. Adey, S. Akçay, M. Bordewich, T. Breckon

{"title":"Autoencoders Without Reconstruction for Textural Anomaly Detection","authors":"Philip A. Adey, S. Akçay, M. Bordewich, T. Breckon","doi":"10.1109/IJCNN52387.2021.9533804","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533804","url":null,"abstract":"Automatic anomaly detection in natural textures is a key component within quality control for a range of high-speed, high-yield manufacturing industries that rely on camera-based visual inspection techniques. Targeting anomaly detection through the use of autoencoder reconstruction error readily facilitates training on an often more plentiful set of non-anomalous samples, without the explicit need for a representative set of anomalous training samples that may be difficult to source. Unfortunately, autoencoders struggle to reconstruct high-frequency visual information and therefore, such approaches often fail to achieve a low enough reconstruction error for non-anomalous pixels. In this paper, we propose a new approach in which the autoencoder is trained to directly output the desired per-pixel measure of abnormality without first having to perform reconstruction. This is achieved by corrupting training samples with noise and then predicting how pixels need to be shifted so as to remove the noise. Our direct approach enables the model to compress anomaly scores for normal pixels into a tight bound close to zero, resulting in very clean anomaly segmentations that significantly improve performance. We also introduce the Reflected ReLU output activation function that better facilitates training under this direct regime by leaving values that fall within the image dynamic range unmodified. Overall, an average area under the ROC curve of 96% is achieved on the texture classes of the MVTecAD benchmark dataset, surpassing that achieved by all current state-of-the-art methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132768777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3