6,751 Hits in 6.5 sec

A Generic Semi-supervised Deep Learning-Based Approach for Automated Surface Inspection

Xiaoqing Zheng, Hongcheng Wang, Jie Chen, Yaguang Kong, Song Zheng
2020 IEEE Access  
In this paper, a generic semi-supervised deep learning-based approach for ASI that requires a small quantity of labeled training data is proposed.  ...  INDEX TERMS Automated surface inspection, defect detection, deep learning, machine vision, MixMatch, semi-supervised learning.  ...  Semi-supervised learning can achieve similar or even better precision than supervised learning but uses fewer labeling samples.  ... 
doi:10.1109/access.2020.3003588 fatcat:wm3gcgqaq5dgzpaeebtiiysmwi

Medical Image Segmentation with 3D Convolutional Neural Networks: A Survey [article]

S Niyas, S J Pawan, M Anand Kumar, Jeny Rajan
2022 arXiv   pre-print
At present, convolutional neural networks (CNN) are the preferred choice for medical image analysis.  ...  In addition, with the rapid advancements in three-dimensional (3D) imaging systems and the availability of excellent hardware and software support to process large volumes of data, 3D deep learning methods  ...  The method uses a semi-supervised training with a mix of labeled and unlabeled images.  ... 
arXiv:2108.08467v3 fatcat:s2rzghycjbczpparmrflsdzujq

Target Detection Network for SAR Images Based on Semi-Supervised Learning and Attention Mechanism

Di Wei, Yuang Du, Lan Du, Lu Li
2021 Remote Sensing  
target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm.  ...  Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper.  ...  Therefore, the target detection network can be trained by a semi-supervised learning method using a small number of target-level labeled training samples and a large number of imagelevel labeled training  ... 
doi:10.3390/rs13142686 fatcat:hnegr6edwfgfxfl67s5x4hijzq

Hybrid Graph Convolutional Network for Semi-supervised Retinal Image Classification

Guanghua Zhang, Jing Pan, Zhaoxia Zhang, Heng Zhang, Changyuan Xing, Bin Sun, Ming Li
2021 IEEE Access  
Hence we proposes a semi-supervised retinal image classification method by a Hybrid Graph Convolutional Network (HGCN).  ...  INDEX TERMS Retinal image classification, semi-supervised, graph convolutional network, modularitybased graph learning.  ...  To address semi-supervised retinal image classification problem in DR diagnosis, this paper builds a Hybrid Graph Convolutional Network (HGCN) as learning from very few labeled images with disease grading  ... 
doi:10.1109/access.2021.3061690 fatcat:mod2mr3kt5a6fn5iwguocplnjq

Semi-Supervised Semantic Segmentation using Adversarial Learning for Pavement Crack Detection

Gang Li, Jian Wan, Shuanhai He, Qiangwei Liu, Biao Ma
2020 IEEE Access  
Compared with existing methods, not only can our method detect different types of cracks, but also be particularly effective when only a few labeled are available: when using 118 crack images with a resolution  ...  INDEX TERMS Adversarial learning, crack detection, semi-supervised learning, semantic segmentation. 51446 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  The last line is the prediction results obtained by training the model with 50% labeled images and 50% unlabeled images using the semi-supervised learning method.  ... 
doi:10.1109/access.2020.2980086 fatcat:sttf5gxwczdufobpeher3u2cpy

Emotion Interaction Recognition Based on Deep Adversarial Network in Interactive Design for Intelligent Robot

Xiang Chen, Lijun Xu, Hua Wei, Zhongan Shang, Tingyu Zhang, Linghao Zhang
2019 IEEE Access  
Finally, we employ a semi-supervised training strategy to optimize the parameters of GAN and use the trained network to process videos.  ...  INDEX TERMS Emotional interaction, adversarial network, deep learning, softmax layer, artificial intelligence, interaction robot, semantic feature.  ...  In the generation model, a neural network structure with three-layer convolution and three-layer pooling convolution is used as the context feature learning model.  ... 
doi:10.1109/access.2019.2953882 fatcat:t334otxcrrac5ectsjgzszgoym

Semi-Supervised Cervical Dysplasia Classification With Learnable Graph Convolutional Network [article]

Yanglan Ou, Yuan Xue, Ye Yuan, Tao Xu, Vincent Pisztora, Jia Li, Xiaolei Huang
2020 arXiv   pre-print
To alleviate the need for much manual annotation, we propose a novel graph convolutional network (GCN) based semi-supervised classification model that can be trained with fewer annotations.  ...  In existing GCNs, graphs are constructed with fixed features and can not be updated during the learning process. This limits their ability to exploit new features learned during graph convolution.  ...  More specifically, we propose a semi-supervised approach based on graph embedding and visual features extracted with convolutional neural networks for cervical dysplasia classification.  ... 
arXiv:2004.00191v1 fatcat:mvyw733b5jgnfedopv3jyvptsq


C. Liu, Y. Zhang, Y. Ou
2020 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
To reduce the burden of data preparation and improve the performance on full-resolution data, the network is trained through semi-supervised learning with image patches at both reduced-resolution and full-resolution  ...  The FEM regroups the extracted features and combines the spectral feature of the MS image with the structure feature of the PAN image.  ...  ., 2017) used semi-supervised learning to predict depth map from monocular images.  ... 
doi:10.5194/isprs-annals-v-3-2020-255-2020 fatcat:nvh7rzniqjbnbkimagf6zovd4e

SSCV-GANs:Semi-Supervised Complex-Valued GANs for PolSAR Image Classification

Xiufang Li, Qigong Sun, LingLing Li, Xu Liu, Hongying Liu, Licheng Jiao, Fang Liu
2020 IEEE Access  
INDEX TERMS Polarimetric synthetic aperture, image classification, complex-valued operations, generative adversarial networks (GANs), semi-supervised learning. 146560 This work is licensed under a Creative  ...  On the other hand, we also present a new complex-valued GANs together with semisupervised learning to alleviate the problem of insufficient labeled data.  ...  [56] proposed a semi-supervised learning method, in this model, GANs are trained and obtained promising classification results with fewer labeled samples. III.  ... 
doi:10.1109/access.2020.3004591 fatcat:zyh5fxaiczdc3n7q6x7uybauda

Semi-supervised Auto-encoder Graph Network for Diabetic Retinopathy Grading

YuJie Li, Zhang Song, SunKyoung Kang, SungTae Jung, Wenpei Kang
2021 IEEE Access  
Finally, we operate Graph Convolutional Neural Network (GCN) to grade retinal samples from extracted features and their correlations.  ...  Recently, researches on deep learning-based retinal image classification have accelerated outstanding improvements in DR grading task.  ...  Finally, a convolutional graph network operates graph feature learning with the help of the learned neighbor correlations to output the grades of each input image.  ... 
doi:10.1109/access.2021.3119434 fatcat:pf465hyztjflhkglxs7lycmd3m

Convolutional Clustering for Unsupervised Learning [article]

Aysegul Dundar, Jonghoon Jin, Eugenio Culurciello
2016 arXiv   pre-print
We further show that learning the connection between the layers of a deep convolutional neural network improves its ability to be trained on a smaller amount of labeled data.  ...  Such reliance on large amounts of labeled data can be relaxed by exploiting hierarchical features via unsupervised learning techniques.  ...  Examples include unsupervised, supervised, and semi-supervised learning.  ... 
arXiv:1511.06241v2 fatcat:feytfrjmazc3zb77nhbinaynca

Semi-Supervised Deep Learning for Fully Convolutional Networks [article]

Christoph Baur, Shadi Albarqouni, Nassir Navab
2017 arXiv   pre-print
We lift the concept of auxiliary manifold embedding for semi-supervised learning to FCNs with the help of Random Feature Embedding.  ...  The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data for training.  ...  Benedikt Wiestler, from the Neuroradiology department of Klinikum Rechts der Isar for providing us with their MRI MS Lesion dataset.  ... 
arXiv:1703.06000v2 fatcat:ht542v2g6jbazcm7fbiey5o6ay

Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images [article]

Bruno Lecouat, Ken Chang, Chuan-Sheng Foo, Balagopal Unnikrishnan, James M. Brown, Houssam Zenati, Andrew Beers, Vijay Chandrasekhar, Jayashree Kalpathy-Cramer, Pavitra Krishnaswamy
2018 arXiv   pre-print
Semi-supervised generative adversarial network (GAN) approaches offer a means to learn from limited labeled data alongside larger unlabeled datasets, but have not been applied to discern fine-scale, sparse  ...  Our semi-supervised approach achieves high AUC with just 10-20 labeled training images, and outperforms the supervised baselines by upto 15% when less than 30% of the training dataset is labeled.  ...  Acknowledgments This project was supported by funding from the Deep Learning 2.0 program at A*STAR, Singapore, and a training grant from the US National Institute of Biomedical Imaging and Bioengineering  ... 
arXiv:1812.07832v1 fatcat:geoenexikfc6bgpne4fwjogbky

Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification [article]

Zilong Zhong, Jonathan Li, David A. Clausi, Alexander Wong
2019 IEEE Transactions on Cybernetics   pre-print
In this paper, we address the hyperspectral image (HSI) classification task with a generative adversarial network and conditional random field (GAN-CRF) -based framework, which integrates a semi-supervised  ...  deep learning and a probabilistic graphical model, and make three contributions.  ...  Third, we integrated a probabilistic graphical model with a semi-supervised deep learning model to refine HSI classification maps.  ... 
doi:10.1109/tcyb.2019.2915094 pmid:31170085 arXiv:1905.04621v1 fatcat:mnjbvq4esfcmlaplmu5iuttfcy

Generative ScatterNet Hybrid Deep Learning (G-SHDL) Network with Structural Priors for Semantic Image Segmentation [article]

Amarjot Singh, Nick Kingsbury
2018 arXiv   pre-print
This paper proposes a generative ScatterNet hybrid deep learning (G-SHDL) network for semantic image segmentation.  ...  The G-SHDL network produces state-of-the-art classification performance against unsupervised and semi-supervised learning on two image datasets.  ...  from a smaller feature space. • Advantages over supervised learning: With G-SHDL only a fraction of the training samples need to be labelled, whereas supervised networks require large labelled training  ... 
arXiv:1802.03374v2 fatcat:rrd7wdfp4baqvdu4ryi5pizkyu
« Previous Showing results 1 — 15 out of 6,751 results