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.
Filters
Impact of Colour Variation on Robustness of Deep Neural Networks
[article]
2022
arXiv
pre-print
Preserved Fulltext
Experimental results indicate that these robust training techniques can improve the robustness of deep networks to color variation. ...
Deep neural networks (DNNs) have have shown state-of-the-art performance for computer vision applications like image classification, segmentation and object detection. ...
[18] analyzed the impact of colour on robustness of widely used deep networks. ...
arXiv:2209.02832v1
fatcat:qbhk63szqjgzjgsvloeni2mebq
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. ...
Therefore, the goal of this paper is to study the robustness of these models under different hue shifts. ...
Recently, De and Pedersen [44] investigated the impact of colour on the robustness of deep neural networks where they have synthetically generated colour distorted images using the publicly available ...
doi:10.2352/ei.2022.34.15.color-156
fatcat:2srpmotmo5cczbo2tty4i4ej24
Exploring Effects of Colour and Image Quality in Semantic Segmentation by Deep Learning Methods
2022
Journal of 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.
One of the major challenges in benchmarking robust deep learning-based computer vision models is lack of challenging data covering different quality and colour parameters. ...
Recent advances in convolutional neural networks and vision transformers have brought about a revolution in the area of computer vision. ...
Generally, deep neural networks are trained on the RGB colour space. ...
doi:10.2352/j.imagingsci.technol.2022.66.5.050401
fatcat:ehwyzfbmzbeknitpr6dvv4xwzm
SURVEY ON TRAFFIC SIGN DETECTION AND RECOGNITION USING AI AND ML
2024
International Research Journal of Modernization in Engineering Technology and Science
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 2024; you can also visit the original URL.
The file type is application/pdf.
For those methodologies within the purview of this review lacking comparative analyses on publicly available datasets, we undertake the initiative of reimplementation, enabling a comparative evaluation ...
, the intricacies of driving scenarios, and instances of occlusion. ...
traffic sign identification and recognition HCI robust detection of traffic signs using global and local directed edge magnitude patterns based on colour HSV Creation of a visual perception model for ...
doi:10.56726/irjmets50792
fatcat:mz5zo2mx5nhizilxyldqs36uui
On the Impact of Illumination-Invariant Image Pre-transformation for Contemporary Automotive Semantic Scene Understanding
2018
2018 IEEE Intelligent Vehicles Symposium (IV)
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.
By using an illumination invariant pre-process, to reduce the impact of environmental illumination changes, we show that the performance of deep convolutional neural network based scene understanding and ...
In addition, we propose a robust approach based on using an illumination-invariant image representation, combined with the chromatic component of a perceptual colour-space to improve contemporary automotive ...
CONCLUSION In this paper, we present the impact of illuminationinvariant image pre-transformation on contemporay automotive semantic scene understanding using deep convolutional neural networks (SegNet ...
doi:10.1109/ivs.2018.8500664
dblp:conf/ivs/AlshammariAB18
fatcat:fr5iu2jcbre5necqt2pxgxqb64
Robustness of convolutional neural networks to physiological electrocardiogram noise
2021
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
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.
Notably, when the network trained on clean data was used to classify the noisy datasets, performance decreases of up to 0.18 in F1 scores were seen. ...
We conclude that physiological ECG noise impacts classification using deep learning methods and careful consideration should be given to the inclusion of noisy ECG signals in the training data when developing ...
Thanks to Claudia Nagel from Karlsruhe Institute of Technology for advice on the ECGdeli software and help obtaining the Lund noise model code. ...
doi:10.1098/rsta.2020.0262
pmid:34689617
pmcid:PMC8543045
fatcat:sstlfz2bjfa5xgyx2zeqgjd2lu
Indirect cutting tool wear classification using deep learning and chip colour analysis
2020
The International Journal of Advanced Manufacturing 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 2020; you can also visit the original URL.
The file type is application/pdf.
The procedure extracts different indicators from the RGB and HSV image channels and instructs a neural network for classifying the chips, based on tool state conditions. ...
The feasibility of the deep learning approach for indirectly understanding the tool wear from the chip colour characterisation is confirmed. ...
A review of the impact of convolutional neural networks in manufacturing can be found in [13] and [14] . ...
doi:10.1007/s00170-020-06055-6
fatcat:kmobuyfbzbejdjg6dz5hduvqpe
Survival study on cyclone prediction methods with remote sensing images
2022
International Journal of Health Sciences
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.
It included the number of interrelated features like eye, cyclone pathway, wind speed, generated storm surges, rainfall intensity and so on. ...
In order to address these issues, cyclone prediction can be carried out using deep leaning methods. ...
The red colour bar and green colour bar denotes the cyclone prediction time of scene classification network architecture frameworkand attention mechanism-based deep supervision network (ADS-Net) correspondingly ...
doi:10.53730/ijhs.v6ns1.6668
fatcat:g4gdygi7l5el5eynoqgvebvmze
Face Emotion Recognition (FER) Using Convolutional Neural Network (CNN) in Machine Learning
2024
International Journal for Research in Applied Science and Engineering 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 2024; you can also visit the original URL.
The file type is application/pdf.
This paper offers a detailed examination of the role of Convolutional Neural Networks (CNNs) in advancing FER methodologies. ...
The discussion emphasizes the adaptability and robustness of CNNs in addressing the complexities of facial emotion recognition. ...
and optimize the training of deep neural networks. ...
doi:10.22214/ijraset.2024.58077
fatcat:4bfmofqkgngcrdy7rvdnc6ehjm
A Computational Modelling and Algorithmic Design Approach of Digital Watermarking in Deep Neural Networks
2020
Advances in Science, Technology and Engineering Systems
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.
to demonstrate the potential of watermarking neural networks. ...
This research addresses digital watermarking in deep neural networks and with comprehensive experiments through computational modeling and algorithm design, we examine the performance of the built system ...
In this the input of the deep learning algorithm is the colour image and watermark to embed inside the colour image to watermark the deep Neural Network (DNN). ...
doi:10.25046/aj0506187
fatcat:7mv5wcjrwjdabojrjfkcpf4qqa
Model Fooling Attacks Against Medical Imaging: A Short Survey
2020
Information & Security An International Journal
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.
Acknowledgements This research is partially funded by the Cyber Security Network of Competence Centres for Europe (CyberSec4Europe) project of the Horizon 2020 SU-ICT-03-2018 program. ...
One of the challenges concerns adversarial attacks and the shakiness of deep decisions made by neural networks. 36 This fundamental lack of robustness could be one avenue of future research. ...
As an example of a weakness, Afifi and Brown explore how white balance of photography impact the performance of deep neural networks, 2 while authors of 21 generated adversarial noise for fooling the neural ...
doi:10.11610/isij.4615
fatcat:vg5xo6wiwfgk5pnm66d2bfgi5u
Evaluation of deep learning techniques for plant disease detection
2024
Computer Science and Information Systems
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 2024; you can also visit the original URL.
The file type is application/pdf.
However, the great diversity of proposed solutions leads us to the need to study them, present possible situations for their improvement, such as image preprocessing, and analyse the robustness of the ...
By training with pictures of affected crops and healthy crops, artificial intelligence techniques learn to distinguish one from the other. ...
Deep Learning techniques, particularly Convolutional Neural Networks, rely on weight optimisations, searching for maxima in the parameter space. ...
doi:10.2298/csis221222073m
fatcat:n66tlh7dsvgorjod6hou5pmr3a
Broad-Leaf Weed Detection in Pasture
2018
2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
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.
Both conventional machine learning algorithms and deep learning methods have been explored and compared to achieve high detection accuracy and robustness in real-world environments. ...
The proposed deep learning method has achieved 96.88% accuracy and is capable of detecting weeds in different pastures under various representative outdoor lighting conditions. ...
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Maxwell Titan X GPU used for this research. ...
doi:10.1109/icivc.2018.8492831
fatcat:qlswf4pr45dwbbzhrxnoqouqru
Establishment of Neural Networks Robust to Label Noise
[article]
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
It can have a considerable impact on the performance of image classification models, particularly deep neural networks, which are especially susceptible because they have a strong propensity to memorise ...
We are not efficiently able to demonstrate the influence of the transition matrix noise correction on robustness enhancements due to our inability to correctly tune the complex convolutional neural network ...
Deep neural networks can be more susceptible to label noise because they have a larger propensity to memorise noisy labels, which can have a negative impact on their capacity to generalize [9] [10] ...
arXiv:2211.15279v2
fatcat:riqbrxw7tndxnjrcy6ejr2vvsm
Fault Tolerance of Neural Networks in Adversarial Settings
[article]
2019
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.
Other Versions
Specifically, this work studies the impact of the fault tolerance of the Neural Network on training the model by adding noise to the input (Adversarial Robustness) and noise to the gradients (Differential ...
To this extent, the trade-off between fault tolerance, privacy and adversarial robustness is evaluated for the specific case of Deep Neural Networks, by considering two adversarial settings under a security ...
Under the security threat model, the impact of fault tolerance on adversarially robust neural networks is evaluated and it is shown training neural networks using provably robust training algorithms results ...
arXiv:1910.13875v1
fatcat:vk6fxfb2rrdapamwsehbzt2bku
« Previous
Showing results 1 — 15 out of 14,509 results