Search results for "Deep Learning"

Learning Flow-Based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision

2020

Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training. We propose a novel Flow-based Feature Warping Model (FFWM) which can learn to synthesize photo-realistic and illumination preserving frontal images with illumination inconsistent supervision. Specifically, an Illumination Preserving Module (IPM) is proposed to learn illumination preserving image synthesis from illumination inconsistent image pairs. IPM includes two pathways which collaborate to ensure the synthesized frontal images are illumination preserving and wit…

Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation

2021

International audience; Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively i…

Proposition of Convolutional Neural Network Based System for Skin Cancer Detection

2019

Skin cancer automated diagnosis tools play a vital role in timely screening, helping dermatologists focus on melanoma cases. Best arts on automated melanoma screening use deep learning-based approaches, especially deep convolutional neural networks (CNN) to improve performances. Because of the large number of parameters that could be involved during training in CNN many training samples are needed to avoid overfitting problem. Gabor filtering can efficiently extract spatial information including edges and textures, which may reduce the features extraction burden to CNN. In this paper, we proposed a Gabor Convolutional Network (GCN) model to improve the performance of automated diagnosis of …

Combination Of Handcrafted And Deep Learning-Based Features For 3d Mesh Quality Assessment

2020

We propose in this paper a novel objective method to evaluate the perceived visual quality of 3D meshes. The proposed method in no-reference, it relies only on the distorted mesh for the quality estimation. It is based on a pre-trained convolutional neural network (i.e VGG to extract features from the distorted mesh) and handcrafted features extracted directly from the 3D mesh (i.e curvature and dihedral angle). A General Regression Neural Network (GRNN) is used to learn the statistical parameters of the feature vectors and estimate the quality score. Experimental results from for subjective databases (LIRIS masking, LIRIS/EPFL generalpurpose, UWB compression and LEETA simplification) and c…

No-reference mesh visual quality assessment via ensemble of convolutional neural networks and compact multi-linear pooling

2020

Abstract Blind or No reference quality evaluation is a challenging issue since it is done without access to the original content. In this work, we propose a method based on deep learning for the mesh visual quality assessment without reference. For a given 3D model, we first compute its mesh saliency. Then, we extract views from the 3D mesh and the corresponding mesh saliency. After that, the views are split into small patches that are filtered using a saliency threshold. Only the salient patches are selected and used as input data. After that, three pre-trained deep convolutional neural networks are employed for feature learning: VGG, AlexNet, and ResNet. Each network is fine-tuned and pro…

Deep Learning for Resource-Limited Devices

2020

In recent years, deep neural networks have revolutionized the development of intelligent systems and applications in many areas. Despite their numerous advantages and potentials, these intelligent models still suffer from several issues. Among them, the fact that they became very complex with millions of parameters. That is, requiring more resources and time, and being unsuitable for small restricted devices. To contribute in this direction, this paper presents (1) some state-of-the-art lightweight architectures that were specifically designed for small-sized devices, and (2) some recent solutions that have been proposed to optimize/compress classical deep neural networks to allow their dep…

Towards A Deep-Learning-Based Methodology for Supporting Satire Detection (S)

2021

Automated quality control of next generation sequencing data using machine learning

2019

AbstractControlling quality of next generation sequencing (NGS) data files is a necessary but complex task. To address this problem, we statistically characterized common NGS quality features and developed a novel quality control procedure involving tree-based and deep learning classification algorithms. Predictive models, validated on internal data and external disease diagnostic datasets, are to some extent generalizable to data from unseen species. The derived statistical guidelines and predictive models represent a valuable resource for users of NGS data to better understand quality issues and perform automatic quality control. Our guidelines and software are available at the following …

Hybrid 3D-ResNet Deep Learning Model for Automatic Segmentation of Thoracic Organs at Risk in CT Images

2020

In image radiation therapy, accurate segmentation of organs at risk (OARs) is a very essential task and has clinical applications in cancer treatment. The segmentation of organs close to lung, breast, or esophageal cancer is a routine and time-consuming process. The automatic segmentation of organs at risk would be an essential part of treatment planning for patients suffering radiotherapy. The position and shape variation, morphology inherent and low soft tissue contrast between neighboring organs across each patient’s scans is the challenging task for automatic segmentation of OARs in Computed Tomography (CT) images. The objective of this paper is to use automatic segmentation of the orga…

Deep learning model deploying on embedded skin cancer diagnostic device

2020

The number of research papers, where neural networks are applied in medical image analysis is growing. There is a proof that Convolutional Neural Networks (CNN) are able to differentiate skin cancer from nevi with greater accuracy than experienced specialists on average (sensitivity 82% and 73% accordingly).1 Team's latest research2 allows achieving even greater accuracy, by using specific narrow-band illumination. Nevertheless, the overall probability of early skin cancer detection depends on the availability of diagnostic tools. If screening tools will be available to a high number of general practices, the chance of disease detection will increase. The previous research3 shows that scala…