Improving discrimination ability of convolutional neural networks by hybrid learning

2015 ◽  
Vol 19 (1) ◽  
pp. 1-9 ◽  
Author(s):  
In-Jung Kim ◽  
Changbeom Choi ◽  
Sang-Heon Lee
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Hybrid Learning ◽  
Discrimination Ability

scholarly journals Investigating the Discrimination Ability of 3D Convolutional Neural Networks Applied to Altered Brain MRI Parametric Maps

2021 ◽  
Author(s):  
Giulia Maria Mattia ◽  
Federico Nemmi ◽  
Edouard Villain ◽  
Marie-Véronique Le Lann ◽  
Xavier Franceries ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Performance ◽  
Brain Mri ◽  
Brain Regions ◽  
Target Region ◽  
Discrimination Ability ◽  
Weighted Magnetic Resonance Imaging ◽  
The Brain ◽  
Parametric Maps

Convolutional neural networks are gradually being recognized in the neuroimaging community as a powerful tool for image analysis. In the present study, we tested the ability of 3D convolutional neural networks to discriminate between whole-brain parametric maps obtained from diffusion-weighted magnetic resonance imaging. Original parametric maps were subjected to intensity-based region-specific alterations, to create altered maps. To analyze how position, size and intensity of altered regions affected the networks’ learning process, we generated monoregion and biregion maps by systematically modifying the size and intensity of one or two brain regions in each image. We assessed network performance over a range of intensity increases and combinations of maps, carrying out 10-fold cross-validation and using a hold-out set for testing. We then tested the networks trained with monoregion images on the corresponding biregion images and vice versa. Results showed an inversely proportional link between size and intensity for the monoregion networks, in that the larger the region, the smaller the increase in intensity needed to achieve good performances. Accuracy was better for biregion networks than for their monoregion counterparts, showing that altering more than one region in the brain can improve discrimination. Monoregion networks correctly detected their target region in biregion maps, whereas biregion networks could only detect one of the two target regions at most. Biregion networks therefore learned a more complex pattern that was absent from the monoregion images. This deep learning approach could be tailored to explore the behavior of other convolutional neural networks for other regions of interest. <br>

scholarly journals Investigating the Discrimination Ability of 3D Convolutional Neural Networks Applied to Altered Brain MRI Parametric Maps

2021 ◽  
Author(s):  
Giulia Maria Mattia ◽  
Federico Nemmi ◽  
Edouard Villain ◽  
Marie-Véronique Le Lann ◽  
Xavier Franceries ◽  
...  
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Performance ◽  
Brain Mri ◽  
Brain Regions ◽  
Target Region ◽  
Discrimination Ability ◽  
Weighted Magnetic Resonance Imaging ◽  
The Brain ◽  
Parametric Maps

Convolutional neural networks are gradually being recognized in the neuroimaging community as a powerful tool for image analysis. In the present study, we tested the ability of 3D convolutional neural networks to discriminate between whole-brain parametric maps obtained from diffusion-weighted magnetic resonance imaging. Original parametric maps were subjected to intensity-based region-specific alterations, to create altered maps. To analyze how position, size and intensity of altered regions affected the networks’ learning process, we generated monoregion and biregion maps by systematically modifying the size and intensity of one or two brain regions in each image. We assessed network performance over a range of intensity increases and combinations of maps, carrying out 10-fold cross-validation and using a hold-out set for testing. We then tested the networks trained with monoregion images on the corresponding biregion images and vice versa. Results showed an inversely proportional link between size and intensity for the monoregion networks, in that the larger the region, the smaller the increase in intensity needed to achieve good performances. Accuracy was better for biregion networks than for their monoregion counterparts, showing that altering more than one region in the brain can improve discrimination. Monoregion networks correctly detected their target region in biregion maps, whereas biregion networks could only detect one of the two target regions at most. Biregion networks therefore learned a more complex pattern that was absent from the monoregion images. This deep learning approach could be tailored to explore the behavior of other convolutional neural networks for other regions of interest. <br>

Traffic Lights Detection in adverse conditions using Convolutional Neural Networks

2018 ◽  
Author(s):  
George Symeonidis ◽  
Peter P. Groumpos ◽  
Evangelos Dermatas
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Traffic Lights ◽  
Adverse Conditions

CNN-based Classification of Degraded Images

2020 ◽  
Vol 2020 (10) ◽  
pp. 28-1-28-7 ◽  
Author(s):  
Kazuki Endo ◽  
Masayuki Tanaka ◽  
Masatoshi Okutomi
Keyword(s):  
Neural Networks ◽  
Image Restoration ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Deep Convolutional Neural Networks ◽  
Alternative Approach ◽  
Degraded Image ◽  
Degraded Images ◽  
Straightforward Approach

Classification of degraded images is very important in practice because images are usually degraded by compression, noise, blurring, etc. Nevertheless, most of the research in image classification only focuses on clean images without any degradation. Some papers have already proposed deep convolutional neural networks composed of an image restoration network and a classification network to classify degraded images. This paper proposes an alternative approach in which we use a degraded image and an additional degradation parameter for classification. The proposed classification network has two inputs which are the degraded image and the degradation parameter. The estimation network of degradation parameters is also incorporated if degradation parameters of degraded images are unknown. The experimental results showed that the proposed method outperforms a straightforward approach where the classification network is trained with degraded images only.

Convolutional Neural Networks for Underwater Pipeline Segmentation using Imperfect Datasets

2021 ◽  
Author(s):  
Edgar Medina ◽  
Roberto Campos ◽  
Jose Gabriel R. C. Gomes ◽  
Mariane R. Petraglia ◽  
Antonio Petraglia
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Underwater Pipeline
Sign in / Sign up

Export Citation Format

Share Document