Search results for "Artificial"
showing 10 items of 7394 documents
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…
Fallzahlplanung in referenzkontrollierten Diagnosestudien
2002
Purpose: A tutorial illustration of a flexible approach to determine the sample size in reference-controlled diagnostic trials. Materials and Methods: Assuming the usual setting of a new diagnostic method to be compared with a reference method, the emphasis is on the sensitivity of the new method in comparison with the reference method, using a binary outcome (positive versus negative) for both methods. Based on the confidence interval of the sensitivity, a simple but flexible procedure for determining the sample size is described, which incorporates clinically interpretable information. The procedure is illustrated by the fictious planning of a trial to assess the diagnostic value of MRI v…
Affine Illumination Compensation on Hyperspectral/Multiangular Remote Sensing Images
2011
The huge amount of information some of the new optical satellites developed nowadays will create demands to quickly and reliably compensate for changes in the atmospheric transmittance and varying solar illumination conditions. In this paper three different forms of affine transformation models (general, particular and diagonal) are considered as candidates for rapid compensation of illumination variations. They are tested on a group of three pairs of CHRISPROBA radiance images obtained in a test field in Barrax (Spain), and where there is a difference in the atmospheric as well as in the geometrical acquisition conditions. Results indicate that the proposed methodology is satisfactory for …
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…
The Application of Optimal Topic Sequence in Adaptive e-Learning Systems
2016
In an adaptive e-learning system an opportunity to choose a course topic sequence is given to ensure personalization. The topic sequence can be obtained from three sources: teacher-offered topic sequence that is based on teacher’s pedagogical experience; learner’s free choice that is based on indicated links between topics, and, finally, the optimal topic sequence acquisition method described in this article. The optimal topic sequence is based on previous learners’ experience. With the help of the optimal topic sequence method, data about previous learners’ course topic sequence and course results are obtained. After the data analysis the optimal topic sequence for the specific course is o…
Artificial Intelligence in Monitoring and Diagnostics of Electrical Energy Conversion Systems
2020
Diagnostics and prognostics of electrical energy conversion systems are moving forward with the rapid development of IT and artificial intelligence possibilities. This also broadens the horizons for classical and advanced condition and operation monitoring techniques, resulting in more accurate fault detection, degradation prognosis and calculation of remaining life of energy conversion systems, utilized in every aspect and field of industry today. This paper gives an overview of the necessity for condition monitoring and diagnostics of the mentioned systems, explaining the classical and advanced techniques for diagnostics. Methodology to diagnose and prognose the energy conversion units, w…