2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)最新文献

筛选

英文中文

On the Transferability of Adversarial Examples between Encrypted Models 论加密模型间对抗性示例的可转移性

2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2022-09-07 DOI: 10.1109/ISPACS57703.2022.10082844

Miki Tanaka, I. Echizen, H. Kiya

引用次数: 2

Connection Reduction of DenseNet for Image Recognition 用于图像识别的DenseNet连接缩减

2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2022-08-02 DOI: 10.1109/ISPACS57703.2022.10082842

Ruikang Ju, Jen-Shiun Chiang, Chih-Chia Chen, Yu-Shian Lin

{"title":"Connection Reduction of DenseNet for Image Recognition","authors":"Ruikang Ju, Jen-Shiun Chiang, Chih-Chia Chen, Yu-Shian Lin","doi":"10.1109/ISPACS57703.2022.10082842","DOIUrl":"https://doi.org/10.1109/ISPACS57703.2022.10082842","url":null,"abstract":"Convolutional Neural Networks increase depth by stacking convolution layers, and deeper network models perform better in image recognition. Empirical research shows that simply stacking convolution layers does not make the network train better, and skip connection (residual learning) can improve network model performance. For the image classification tasks, models with global densely connected architectures perform well in large datasets like ImageNet, but they are not suitable for small datasets such as CIFAR-10 and SVHN. Different from dense connections, we propose two new algorithms to connect layers in this paper. Baseline is a densely connected network, and the networks connected by the two new algorithms are named ShortNet1 and ShortNet2, respectively. The experimental results of image classification on CIFAR-10 and SVHN show that ShortNet1has a 5% lower test error rate and 25% faster inference time than Baseline. ShortNet2 speeds up inference time by 40% with less loss in test accuracy. Code and pretrained models are available at https://github.com/RuiyangJu/Connection_Reduction/","PeriodicalId":410603,"journal":{"name":"2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133512163","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

Multiple Categories Of Visual Smoke Detection Database 多类别视觉烟雾检测数据库

2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) Pub Date : 2022-07-30 DOI: 10.1109/ISPACS57703.2022.10082827

Y. Gong, X. Ma

{"title":"Multiple Categories Of Visual Smoke Detection Database","authors":"Y. Gong, X. Ma","doi":"10.1109/ISPACS57703.2022.10082827","DOIUrl":"https://doi.org/10.1109/ISPACS57703.2022.10082827","url":null,"abstract":"Smoke detection has become a significant task in associated industries due to the close relationship between the petrochemical industry's smoke emission and its safety production and environmental damage. There are several production situations in the real industrial production environment, including complete combustion of exhaust gas, inadequate combustion of exhaust gas, direct emission of exhaust gas, etc. We discovered that the datasets used in previous research work could only determine whether smoke is present or not, not its type. That is, the dataset's category does not map to real-world production situations, which are not conducive to the precise regulation of the production system. In order to reduce the gap between the algorithm and the actual application so that the new algorithm can more comprehensively cover and solve the actual situations, we created a multi-categories smoke detection database that in-cludes a total of 70196 images. We further conduct the experiment by employing multiple models on the proposed database. The results demonstrate the effectiveness of the proposed database and show that the performance of the current algorithms needs to be improved.","PeriodicalId":410603,"journal":{"name":"2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114972428","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

首页上一页