A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Advancing efficiency and robustness of neural networks for imaging
2020
Preserved Fulltext
More specifically, this work introduces an efficient 3D convolutional neural network architecture, which achieves high performance for segmentation of volumetric medical images, an application previously ...
It investigates domain adaptation and introduces an architecture for adversarial networks tailored for adaptation of segmentation networks. ...
To this end, we investigated and developed methodologies for constructing and training computationally efficient high-performing neural networks for image processing. ...
doi:10.25560/80157
fatcat:mv3q2zargfamrifgqwfycd53mq
Effect of hue shift towards robustness of convolutional neural networks
2022
IS&T International Symposium on Electronic Imaging Science and Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
As a vast majority of the AI enabled systems are based on convolutional neural networks based models which use 3-channel RGB images as input. ...
However, color related changes to images could also impact the performance. Therefore, the goal of this paper is to study the robustness of these models under different hue shifts. ...
Imagenet dataset [45] and conducted detailed experiments using state-of-the-art convolutional neural networks to study the robustness of these networks. ...
doi:10.2352/ei.2022.34.15.color-156
fatcat:2srpmotmo5cczbo2tty4i4ej24
Advances in deep learning for real-time image and video reconstruction and processing
2020
Journal of Real-Time Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Image reconstruction based deep learning can be efficiently performed by using neural networks, in which, weights are determined based on training data. ...
imaging sensors and generates better applications for the emergent capability of highresolution displays. ...
In "Low-Complexity CNN with 1D and 2D Filters for Super-Resolution", the authors propose a low-complexity convolution neural network for image super-resolution. ...
doi:10.1007/s11554-020-01026-2
fatcat:23jzdzkoxfdnrjfeew7bpwy7fm
Special Issue: Capsule Networks and Imaging Science (CNIS)
2021
Neural Processing Letters
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
It contains some of the latest research works that streamlines the research into problems at the intersection of neural networks and imaging science. ...
This special issue on "Capsule Networks and Imaging Science" has investigated the challenges in real-time image processing and proposed novel solutions with different neural network models to process the ...
In this research perspective, this paper proposes a self-organizing capsule neural network and game theory to deliver higher efficiency and robustness in the performing the image processing tasks. ...
doi:10.1007/s11063-021-10550-6
fatcat:recnlgjqzbho3kuvbdievowvsu
CMVF
2003
Proceedings of the 2003 ACM SIGMOD international conference on on Management of data - SIGMOD '03
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2007; you can also visit the original URL.
The file type is application/pdf.
DEMONSTRATION With the use of hybrid structure, CMVF illustrates its great advance in performance against other dimension reduction methods such as the PCA and neural network. ...
The efficiency is gained by using a relatively small number of network inputs and the network training iterations are conducted in the direction of the largest eigenvalues for each feature. 2 Because there ...
doi:10.1145/872841.872842
fatcat:mbj6f47iijgvna2zekgug6c2ee
CMVF
2003
Proceedings of the 2003 ACM SIGMOD international conference on on Management of data - SIGMOD '03
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2007; you can also visit the original URL.
The file type is application/pdf.
DEMONSTRATION With the use of hybrid structure, CMVF illustrates its great advance in performance against other dimension reduction methods such as the PCA and neural network. ...
The efficiency is gained by using a relatively small number of network inputs and the network training iterations are conducted in the direction of the largest eigenvalues for each feature. 2 Because there ...
doi:10.1145/872757.872842
dblp:conf/sigmod/ShenNSHS03
fatcat:vba4n5y4mbgbrnuju5tvjewzma
Advances in facial landmark detection
2018
Biometric Technology Today
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The third and the most important category of recent advances in facial landmark detection is the use of deep neural networks. ...
To achieve robust facial landmark detection for face images in such scenarios, the cutting-edge techniques resort to more sophisticated tools such as Cascaded Shape Regression (CSR) and Deep Neural Networks ...
doi:10.1016/s0969-4765(18)30038-9
fatcat:oz4evam3hfd4fjexiubotqdefm
Comparing Robustness of Pairwise and Multiclass Neural-Network Systems for Face Recognition
2007
EURASIP Journal on Advances in Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper we explore a pairwise neural-network system as an alternative approach to improving the robustness of face recognition. ...
Noise, corruptions and variations in face images can seriously hurt the performance of face recognition systems. ...
Libor Spacek from the University of Essex as well as to the AT&T Laboratories Cambridge for making the Faces94 and ORL face-image data ...
doi:10.1155/2008/468693
fatcat:x25wstziefdppopbdzlpmkqvwm
An Efficient Watermarking Scheme for Medical Data Security With the Aid of Neural Network
2016
Brazilian Archives of Biology and Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In this paper we proposed an efficient watermarking technique for medical data security with the aid of neural network. ...
With the advancement in digital data distribution over the network there has been increase in the need for protection of such data from unauthorized copying or usages. ...
Hence neural network can be utilized for generating watermarking with more efficient and powerful against authentication. ...
doi:10.1590/1678-4324-2016161070
fatcat:p7644zf46fc2lhojlflamciqly
Fine Facet Digital Watermark (FFDW) Mining From The Color Image Using Neural Networks
2011
International Journal of Advanced Computer Science and Applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2013; you can also visit the original URL.
The file type is application/pdf.
On hand watermark methods employ selective Neural Network techniques for watermark embedding efficiently. ...
Similarity Based Superior Self Organizing Maps (SBS_SOM) a neural network algorithm for watermark generation. ...
Reference [4] presented a specific designed full counter-propagation neural network for digital image watermarking. Most of the systems used CPN, BPN and RBF algorithms. ...
doi:10.14569/specialissue.2011.010110
fatcat:lfaqjc4w5na65pgdsnuo3ine2u
Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
First, we present a capsule network that explicitly learns a representation robust to rotation and affine transformation. ...
We posit that more research in this direction combining hardware and learning advancements will power future medical imaging (on-device AI, few-shot prediction, adaptive scanning). ...
The most powerful capability of neural networks is the automatic detection and efficient representation of increasingly higher-order features. ...
arXiv:2005.05431v1
fatcat:z3zewphpxrf4haz7w3erz3xkli
Deep learning based computer-aided diagnosis for neuroimaging data: focused review and future potential
2018
Neuroimmunology and Neuroinflammation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
At the forefront of these advancements is the usage of deep (artificial) neural network architectures that led robust learning based techniques to attack challenging problems such as segmentation and classification ...
DL networks typically require annotations of several images for employing supervised learning techniques and are one of the roadblocks in employing these state of the art networks in various classification ...
At the forefront of these advancements is the usage of deep (artificial) neural network architectures that led robust learning based techniques to attack challenging problems such as segmentation and classification ...
doi:10.20517/2347-8659.2017.68
fatcat:y3j3qtugxzbofk7komyn3ntx4m
Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). ...
We give preliminary definitions on what adversarial attacks and robustness are. After that, we study frequently-used benchmarks and mention theoretically-proved bounds for adversarial robustness. ...
., 2020] Igor Buzhinsky, Arseny Nerinovsky, and Stavros Tripakis. Metrics and methods for robustness evaluation of neural networks with generative models, 2020. [Carlini and Wagner, 2017a] N. ...
arXiv:2011.01539v1
fatcat:e3o47epftbc2rebpdx5yotzriy
A Comparative Approach on Classification of Images with Convolutional Neural Networks
2021
International Journal of Engineering and Advanced Technology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we will study in a systematical manner the efficiency of various Convolutional Neural Networks (CNN) approaches, in respects to the type of architecture and optimization strategies, with ...
Image degradation, such as blurring, or various sources of noise are common reasons for distortion happening during image procurement. ...
INTRODUCTION Convolutional Neural Networks (CNN) approaches for image classification are the state of the art and a high percentage of effort in research is presently aimed toward supplementary developing ...
doi:10.35940/ijeat.d2483.0410421
fatcat:rndehezxejg4hgij74qegckx3m
VCIP 2020 Index
2020
2020 IEEE International Conference on Visual Communications and Image Processing (VCIP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Improving Robustness of DNNs against Comm
Corruptions via Gaussian Adversarial Training
Wan, Zekang
Deep Convolutional Neural Network Based on
Multi-Scale Feature Extraction for Image
Denoising ...
123.0-B-1 FOR
LOSSLESS 4D IMAGE COMPRESSION
Fracastoro, Giulia
NIR image colorization with graph-convolutiona
neural networks
Fu, Hao-Lun
Application of Brain-Computer Interface and
Virtual Reality ...
doi:10.1109/vcip49819.2020.9301896
fatcat:bdh7cuvstzgrbaztnahjdp5s5y
« Previous
Showing results 1 — 15 out of 97,607 results