Pub Date : 2020-01-01DOI: 10.5220/0009823500590067
Silvan Mertes, A. Margraf, Christoph Kommer, Steffen Geinitz, E. André
: Computer vision systems are popular tools for monitoring tasks in highly specialized production environ-ments. The training and configuration, however, still represents a time-consuming task in process automation. Convolutional neural networks have helped to improve the ability to detect even complex anomalies withouth exactly modeling image filters and segmentation strategies for a wide range of application scenarios. In recent publications, image-to-image translation using generative adversarial networks was introduced as a promising strategy to apply patterns to other domains without prior explicit mapping. We propose a new approach for generating augmented data to enable the training of convolutional neural networks for semantic segmentation with a minimum of real labeled data. We present qualitative results and demonstrate the application of our system on textile images of carbon fibers with structural anomalies. This paper compares the potential of image-to-image translation networks with common data augmentation strategies such as image scaling, rotation or mirroring. We train and test on image data acquired from a high resolution camera within an industrial monitoring use case. The experiments show that our system is comparable to common data augmentation approaches. Our approach extends the toolbox of semantic segmentation since it allows for generating more problem-specific training data from sparse input.
{"title":"Data Augmentation for Semantic Segmentation in the Context of Carbon Fiber Defect Detection using Adversarial Learning","authors":"Silvan Mertes, A. Margraf, Christoph Kommer, Steffen Geinitz, E. André","doi":"10.5220/0009823500590067","DOIUrl":"https://doi.org/10.5220/0009823500590067","url":null,"abstract":": Computer vision systems are popular tools for monitoring tasks in highly specialized production environ-ments. The training and configuration, however, still represents a time-consuming task in process automation. Convolutional neural networks have helped to improve the ability to detect even complex anomalies withouth exactly modeling image filters and segmentation strategies for a wide range of application scenarios. In recent publications, image-to-image translation using generative adversarial networks was introduced as a promising strategy to apply patterns to other domains without prior explicit mapping. We propose a new approach for generating augmented data to enable the training of convolutional neural networks for semantic segmentation with a minimum of real labeled data. We present qualitative results and demonstrate the application of our system on textile images of carbon fibers with structural anomalies. This paper compares the potential of image-to-image translation networks with common data augmentation strategies such as image scaling, rotation or mirroring. We train and test on image data acquired from a high resolution camera within an industrial monitoring use case. The experiments show that our system is comparable to common data augmentation approaches. Our approach extends the toolbox of semantic segmentation since it allows for generating more problem-specific training data from sparse input.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"8 1","pages":"59-67"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80123443","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}
Pub Date : 2020-01-01DOI: 10.5220/0009970200420049
Zhi-Chen Yan, Stephanie A. Yu
Recognizing texts in real-world scenes is an important research topic in computer vision. Many deep learning based techniques have been proposed. Such techniques typically follow an encoder-decoder architecture, and use a sequence of feature vectors as the intermediate representation. In this approach, useful 2D spatial information in the input image may be lost due to vector-based encoding. In this paper, we formulate scene text recognition as a spatiotemporal sequence translation problem, and introduce a novel attention based spatiotemporal decoding framework. We first encode an image as a spatiotemporal sequence, which is then translated into a sequence of output characters using the aforementioned decoder. Our encoding and decoding stages are integrated to form an end-to-end trainable deep network. Experimental results on multiple benchmarks, including IIIT5k, SVT, ICDAR and RCTW-17, indicate that our method can significantly outperform conventional attention frameworks.
{"title":"Attention-based Text Recognition in the Wild","authors":"Zhi-Chen Yan, Stephanie A. Yu","doi":"10.5220/0009970200420049","DOIUrl":"https://doi.org/10.5220/0009970200420049","url":null,"abstract":"Recognizing texts in real-world scenes is an important research topic in computer vision. Many deep learning based techniques have been proposed. Such techniques typically follow an encoder-decoder architecture, and use a sequence of feature vectors as the intermediate representation. In this approach, useful 2D spatial information in the input image may be lost due to vector-based encoding. In this paper, we formulate scene text recognition as a spatiotemporal sequence translation problem, and introduce a novel attention based spatiotemporal decoding framework. We first encode an image as a spatiotemporal sequence, which is then translated into a sequence of output characters using the aforementioned decoder. Our encoding and decoding stages are integrated to form an end-to-end trainable deep network. Experimental results on multiple benchmarks, including IIIT5k, SVT, ICDAR and RCTW-17, indicate that our method can significantly outperform conventional attention frameworks.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"51 1","pages":"42-49"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84626687","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}
{"title":"Otolaryngology in World War II.","authors":"F LEDERER","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"38 1","pages":"12"},"PeriodicalIF":0.0,"publicationDate":"1947-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"28836035","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}
{"title":"Progress in surgery in war and peace.","authors":"A M GLICKMAN","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"37 4","pages":"175-7"},"PeriodicalIF":0.0,"publicationDate":"1946-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"28833476","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}
{"title":"A plan to eradicate the common cold.","authors":"N D FABRICANT","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"37 3","pages":"114"},"PeriodicalIF":0.0,"publicationDate":"1946-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"28833475","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}
Pub Date : 1900-01-01DOI: 10.5220/0009885600890097
Pu Chen, Hung-Hsuan Chen
: This paper studies overparameterization on the matrix factorization (MF) model. We confirm that overparameterization can significantly accelerate the optimization of MF with no change in the expressiveness of the learning model. Consequently, modern applications on recommendations based on MF or its variants can largely benefit from our discovery. Specifically, we theoretically derive that applying the vanilla stochastic gradient descent (SGD) on the overparameterized MF model is equivalent to employing gradient descent with momentum and adaptive learning rate on the standard MF model. We empirically compare the overparameterized MF model with the standard MF model based on various optimizers, including vanilla SGD, AdaGrad, Adadelta, RMSprop, and Adam, using several public datasets. The experimental results comply with our analysis – overparameterization converges faster. The overparameterization technique can be applied to various learning-based recommendation models, including deep learning-based recommendation models, e.g., SVD++, nonnegative matrix factorization (NMF), factorization machine (FM), NeuralCF, Wide&Deep, and DeepFM. Therefore, we suggest utilizing the overparameterization technique to accelerate the training speed for the learning-based recommendation models whenever possible, especially when the size of the training dataset is large.
{"title":"Accelerating Matrix Factorization by Overparameterization","authors":"Pu Chen, Hung-Hsuan Chen","doi":"10.5220/0009885600890097","DOIUrl":"https://doi.org/10.5220/0009885600890097","url":null,"abstract":": This paper studies overparameterization on the matrix factorization (MF) model. We confirm that overparameterization can significantly accelerate the optimization of MF with no change in the expressiveness of the learning model. Consequently, modern applications on recommendations based on MF or its variants can largely benefit from our discovery. Specifically, we theoretically derive that applying the vanilla stochastic gradient descent (SGD) on the overparameterized MF model is equivalent to employing gradient descent with momentum and adaptive learning rate on the standard MF model. We empirically compare the overparameterized MF model with the standard MF model based on various optimizers, including vanilla SGD, AdaGrad, Adadelta, RMSprop, and Adam, using several public datasets. The experimental results comply with our analysis – overparameterization converges faster. The overparameterization technique can be applied to various learning-based recommendation models, including deep learning-based recommendation models, e.g., SVD++, nonnegative matrix factorization (NMF), factorization machine (FM), NeuralCF, Wide&Deep, and DeepFM. Therefore, we suggest utilizing the overparameterization technique to accelerate the training speed for the learning-based recommendation models whenever possible, especially when the size of the training dataset is large.","PeriodicalId":88612,"journal":{"name":"News. Phi Delta Epsilon","volume":"20 1","pages":"89-97"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74441175","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：