Search results for "artificial intelligence"

Assessment of qualitative judgements for conditional events in expert systems

1991

Towards a SDN-based architecture for analyzing network traffic in cloud computing infrastructures

2015

Currently, network traffic monitoring tools do not fit well in the monitoring of cloud computing infrastructures. These tools are not integrated with the control plane of the cloud computing stack. This lack of integration causes a deficiency in the handling of the re-usage of IP addresses along virtual machines, a lack of adaption and reaction on highly frequent topology changes, and a lack of accuracy in the metrics gathered for the networking traffic flowing along the cloud infrastructure. The main contribution of this paper is to provide a novel SDN-based architecture to carry out the monitoring of network traffic in cloud infrastructures. The architecture in based on the integration be…

Convolutional Long Short-Term Memory Network for Multitemporal Cloud Detection Over Landmarks

2019

In this work, we propose to exploit both the temporal and spatial correlations in Earth observation satellite images through deep learning methods. In particular, the combination of a U-Net convolutional neural network together with a convolutional long short-term memory (LSTM) layer is proposed. This model is applied for cloud detection on MSG/SEVIRI image time series over selected landmarks. Implementation details are provided and our proposal is compared against a standard SVM and a U-Net without the convolutional LSTM layer but including temporal information too. Experimental results show that this combination of networks exploits both the spatial and temporal dependence and provides st…

Infantile Hemangioma Detection using Deep Learning

2020

Infantile hemangiomas are the most common type of benign tumor which appear in the first weeks of life. As currently there is no robust protocol to monitor and assess the hemangioma status, this study proposes a preliminary method to detect the lesion. Therefore, in this paper we describe a hemangiomas classifier based on a linear convolutional neural network architecture. The challenge was to achieve a good classification using a relatively small internal database of 240 images from 40 different patients. The results are promising as the CNN performance evaluation showed a level of accuracy on the test set of 93.84%. Five metrics were calculated to assess the proposed model performances: a…

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…

Towards General Purpose Object Detection: Deep Dense Grid Based Object Detection

2020

Object detection is one of the most challenging and very important branch of computer vision. Some of the challenging aspect of a detection network is the fact that an object can appear anywhere in the image, be partially occluded by another object, might appear in crowd or have greatly varying scales. Consequently, we propose a fine grained and equally spaced dense grid cells throughout an input image be responsible of detecting an object. We re-purpose an already existing deep state-of-the-art detector or classifier into deep and dense detector. Our dense object detector uses binary class encoding and hence suitable for very large multi-class object detector. We also propose a more flexib…