Deep Convolutional Neural Networks and Noisy Images

Nazaré, Tiago S.; Costa, Gabriel B.; Contato, Welinton A.; Ponti, Moacir Antonelli

doi:10.1007/978-3-319-75193-1_50

Cited by 67 publications

(47 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Preprocessing raw signal data for noise and artifact reduction did not significantly affect classification results in preliminary testing. Prior performance analyses have demonstrated that deep learning models become more robust when trained on noisy data [53], and we suspect that training on raw, unprocessed data may be advantageous for accuracy and transferability when testing across clinical datasets as well. Noisy input data are hypothesized to improve the robustness of deep learning models by stabilizing against distortions in the input [54].…”

Section: Discussionmentioning

confidence: 98%

Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks

Zhang

Fabbri

Upender

et al. 2019

Sleep

View full text Add to dashboard Cite

Study Objectives Polysomnography (PSG) scoring is labor intensive and suffers from variability in inter- and intra-rater reliability. Automated PSG scoring has the potential to reduce the human labor costs and the variability inherent to this task. Deep learning is a form of machine learning that uses neural networks to recognize data patterns by inspecting many examples rather than by following explicit programming. Methods A sleep staging classifier trained using deep learning methods scored PSG data from the Sleep Heart Health Study (SHHS). The training set was composed of 42 560 hours of PSG data from 5213 patients. To capture higher-order data, spectrograms were generated from electroencephalography, electrooculography, and electromyography data and then passed to the neural network. A holdout set of 580 PSGs not included in the training set was used to assess model accuracy and discrimination via weighted F1-score, per-stage accuracy, and Cohen’s kappa (K). Results The optimal neural network model was composed of spectrograms in the input layer feeding into convolutional neural network layers and a long short-term memory layer to achieve a weighted F1-score of 0.87 and K = 0.82. Conclusions The deep learning sleep stage classifier demonstrates excellent accuracy and agreement with expert sleep stage scoring, outperforming human agreement on sleep staging. It achieves comparable or better F1-scores, accuracy, and Cohen’s kappa compared to literature for automated sleep stage scoring of PSG epochs. Accurate automated scoring of other PSG events may eventually allow for fully automated PSG scoring.

show abstract

Section: Discussionmentioning

confidence: 98%

Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks

Zhang

Fabbri

Upender

et al. 2019

Sleep

View full text Add to dashboard Cite

show abstract

“…224 × 224) so we can find several cropped versions of an image with higher resolution; (ii) flipping images horizontally -and also vertically if it makes sense, e.g. in case of remote sensing and astronomical images; (iii) adding noise [44]; (iv) creating new images by using PCA as in the Fancy PCA proposed by [6]. Note that augmentation must be performed preserving the labels.…”

Section: Optimization Algorithmsmentioning

confidence: 99%

“…Even considering tasks that are in principle possible to be addressed via Deep Learning, there are many studies showing that perturbations in the input data, such as noise, can significantly impact the results [44]. An interesting paper showed that deep networks can even fail to classify inverted images [105].…”

Section: Limitations Of Deep Learningmentioning

confidence: 99%

Everything You Wanted to Know about Deep Learning for Computer Vision but Were Afraid to Ask

Ponti¹,

Ribeiro²,

Nazaré³

et al. 2017

2017 30th SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T)

118

View full text Add to dashboard Cite

show abstract

“…Despite the phenomenal success of CNNs in computer vision, they have a weak point. Their image classification performance degrades when fed with noisy images [23][24][25]. Moreover, the deep-learning architecture in image processing at times must face the serious problem of adversarial attacks, in which infinitesimal noise is deliberately added to the images to attack the recognition system and produce misleading recognition [26].…”

Section: Introductionmentioning

confidence: 99%

Comparing U-Net Based Models for Denoising Color Images

Komatsu

Gonsalves

2020

View full text Add to dashboard Cite

Digital images often become corrupted by undesirable noise during the process of acquisition, compression, storage, and transmission. Although the kinds of digital noise are varied, current denoising studies focus on denoising only a single and specific kind of noise using a devoted deep-learning model. Lack of generalization is a major limitation of these models. They cannot be extended to filter image noises other than those for which they are designed. This study deals with the design and training of a generalized deep learning denoising model that can remove five different kinds of noise from any digital image: Gaussian noise, salt-and-pepper noise, clipped whites, clipped blacks, and camera shake. The denoising model is constructed on the standard segmentation U-Net architecture and has three variants—U-Net with Group Normalization, Residual U-Net, and Dense U-Net. The combination of adversarial and L1 norm loss function re-produces sharply denoised images and show performance improvement over the standard U-Net, Denoising Convolutional Neural Network (DnCNN), and Wide Interface Network (WIN5RB) denoising models.

show abstract

Deep Convolutional Neural Networks and Noisy Images

Cited by 67 publications

References 9 publications

Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks

Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks

Everything You Wanted to Know about Deep Learning for Computer Vision but Were Afraid to Ask

Comparing U-Net Based Models for Denoising Color Images

Contact Info

Product

Resources

About