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.
Filters
Magnifying Networks for Histopathological Images with Billions of Pixels
2024
Diagnostics
Preserved Fulltext
Importantly, MagNets process at least five times fewer patches from each whole-slide image than any of the existing end-to-end approaches. ...
Amongst the other benefits conferred by the shift from traditional to digital pathology is the potential to use machine learning for diagnosis, prognosis, and personalization. ...
Introduction One of the most practically important examples of image analysis with billions of pixels can be found in digital pathology and, in particular, in the task of whole-slide image (WSI) classification ...
doi:10.3390/diagnostics14050524
pmid:38472996
pmcid:PMC10930771
fatcat:2nxeewmolrcwhhhg3pfosbx35a
SparseConvMIL: Sparse Convolutional Context-Aware Multiple Instance Learning for Whole Slide Image Classification
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Multiple instance learning (MIL) is the preferred approach for whole slide image classification. ...
This paper presents a novel MIL approach that exploits the spatial relationship of tiles for classifying whole slide images. ...
Indeed, while traditional image weighs less than 1 megapixel -e.g. 0.09 megapixel for images of ImageNet (Deng et al., 2009 ) -whole slide images often contain several billions of pixels at full magnification ...
arXiv:2105.02726v2
fatcat:qk5sqn5cd5dkhm6zv2ecova66m
A survey on deep learning in medical image analysis
2017
Medical Image Analysis
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2017 pre-print arXiv:1702.05747v1 fatcat:zdedepkenraglidf7b4ojxcohiOther Versions
Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. ...
We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks and provide concise overviews of studies per application area. ...
Papers not reporting results on medical image data or only using standard feed-forward neural networks with handcrafted features were excluded. ...
doi:10.1016/j.media.2017.07.005
pmid:28778026
fatcat:esbj72ftwvbgzh6jgw367k73j4
An annotation-free whole-slide training approach to pathological classification of lung cancer types using deep learning
2021
Nature Communications
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 alleviate the burden of such contouring and obtain benefits from scaling up training with numerous WSIs, we develop a method for training neural networks on entire WSIs using only slide-level diagnoses ...
Deep learning for digital pathology is hindered by the extremely high spatial resolution of whole-slide images (WSIs). ...
Trees-Juen Chuang for careful reading and giving advice on this manuscript. We are grateful to the National Center for High-performance Computing for providing computing resources. ...
doi:10.1038/s41467-021-21467-y
pmid:33608558
pmcid:PMC7896045
fatcat:thkwoy5xvbcc5jcnv6hd5nohv4
Fully Convolutional Network for Melanoma Diagnostics
[article]
2018
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 2019; you can also visit the original URL.
The file type is application/pdf.
Then, we devised a novel multi-stride fully convolutional network (FCN) architecture that outperformed other networks trained and evaluated using the same data according to standard metrics. ...
more work is required to improve the network's performance on dermis segmentation. ...
They use a patch-based approach to train their model using their dataset of 58 whole slide images with patch size of 256 × 256 compared with our 512 × 512. ...
arXiv:1806.04765v1
fatcat:ssps2yurbzhzvj2kgkbrutfmdu
Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video
[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.
The two-stream model consists of a spatial stream network for Object Detection and a temporal stream network to leverage motion features for Multiple Object Tracking. ...
In this paper, we propose a two-stream Convolutional Network architecture that performs real-time detection, tracking, and near accident detection of road users in traffic video data. ...
ACKNOWLEDGMENTS The authors would like to thank City of Gainesville for providing real traffic fisheye video data. ...
arXiv:1901.01138v1
fatcat:g6lkg7mskvdmjlrb2tu4r4vacy
ZynqNet: An FPGA-Accelerated Embedded Convolutional Neural Network
[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.
Convolutional Neural Networks (CNNs) presently achieve record-breaking accuracies in all image understanding benchmarks, but have a very high computational complexity. ...
The FPGA accelerator has been synthesized using High-Level Synthesis for the Xilinx Zynq XC-7Z045, and reaches a clock frequency of 200MHz with a device utilization of 80% to 90 %. ...
Acknowledgement First and foremost, I would like to thank my supervisor Emanuel Schmid for the pleasant ...
arXiv:2005.06892v1
fatcat:tduahjb5w5cjromemahngmt3gy
ActivityNet Challenge 2017 Summary
[article]
2017
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.
We would like to thank the authors of the Kinetics dataset for their kind support; and Joao Carreira and Brian Zhang for helpful discussions. ...
In the future, we will improve our framework such as training the whole networks end-to-end. ...
We propose a fast end-to-end Region Convolutional 3D Network (R-C3D) for activity detection in continuous video streams. ...
arXiv:1710.08011v1
fatcat:bc5qhp2cungrdj4j3lebxeoane
A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends
[article]
2024
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 2024; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and image ...
It's crucial to gain a thorough understanding and perform a comparative analysis of these different CNN types to understand their strengths and weaknesses. ...
ACKNOWLEDGEMENTS This work was partially supported by the NYUAD Center for Artificial Intelligence and Robotics (CAIR), funded by Tamkeen under the NYUAD Research Institute Award CG010. ...
arXiv:2402.15490v2
fatcat:lxbsxo3teffixcwel5oyqipcsa
Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3
2019
2019 1st International Conference on Unmanned Vehicle Systems-Oman (UVS)
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.
Several deep learning techniques wererecently proposed based on convolution neural network (CNN)for real-time classification and recognition in computer vision.However, their performance depends on the ...
Several deep learning techniques were recently proposed based on convolution neural network (CNN) for real-time classification and recognition in computer vision. ...
Secondly, we replace the fully connected layers with a convolution layer and make a complete training from end to end for the object detection. 2) Improvements made in YOLO v2: A new competitor for YOLO ...
doi:10.1109/uvs.2019.8658300
fatcat:5wrbqfil6jbo7kzv5ymozbmkty
WeedMap: A large-scale semantic weed mapping framework using aerial multispectral imaging and deep neural network for precision farming
[article]
2018
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1808.00100v1 fatcat:zofcpamslneihfhkm6sqkztfwa
We present a novel weed segmentation and mapping framework that processes multispectral images obtained from an unmanned aerial vehicle (UAV) using a deep neural network (DNN). ...
Additionally, we provide an extensive analysis of 20 trained models, both qualitatively and quantitatively, in order to evaluate the effects of varying input channels and tunable network hyperparameters ...
Abbreviations The following abbreviations are used in this manuscript: ...
arXiv:1808.00100v2
fatcat:ximvjlmgkrbixalpoun3urpiia
Recent Advances in Convolutional Neural Network Acceleration
[article]
2018
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.
In recent years, convolutional neural networks (CNNs) have shown great performance in various fields such as image classification, pattern recognition, and multi-media compression. ...
However, as the dimension of data becomes higher and the CNN architecture becomes more complicated, the end-to-end approach or the combined manner of CNN is computationally intensive, which becomes limitation ...
Single instruction multiple data (SIMD) processors are used on a 32-bit CPU to design a system targeted for ASIC synthesis to perform real-time detection, recognition and segmentation of mega-pixel images ...
arXiv:1807.08596v1
fatcat:jx66ekaofjhqzdbaueal476bvi
Car Detection using Unmanned Aerial Vehicles: Comparison between Faster R-CNN and YOLOv3
[article]
2018
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.
Several deep learning techniques were recently proposed based on convolution neural network (CNN) for real-time classification and recognition in computer vision. ...
One of the major challenges is to use aerial images to accurately detect cars and count them in real-time for traffic monitoring purposes. ...
Secondly, we replace the fully connected layers with a convolution layer and make a complete training from end to end for the object detection. 2) Improvements made in YOLO v2: A new competitor for YOLO ...
arXiv:1812.10968v1
fatcat:ximkbkljxbaebeoojpo2nrujem
Smart Cameras
[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.
Modern cameras use physical components and software to capture, compress and display image data. ...
Over the past 5 years, deep learning solutions have become superior to traditional algorithms for each of these functions. ...
Typically, rate-distortion optimization [125] is fulfilled by minimizing Lagrangian cost J = R + λD, when performing the end-to-end training. ...
arXiv:2002.04705v1
fatcat:277yq2oaujdoxbtqqsq6naodma
Deep Learning-Based Prediction of Molecular Tumor Biomarkers from H&E: A Practical Review
2022
Journal of Personalized Medicine
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.
This article reviews the diverse applications across cancer types and the methodology to train and validate these models on whole slide images. ...
From bottom-up to pathologist-driven to hybrid approaches, the leading trends include a variety of weakly supervised deep learning-based approaches, as well as mechanisms for training strongly supervised ...
From unified memory to streaming to halo exchange, each of these approaches enables end-to-end training of much larger images-but still with current limits around 20 k × 20 k pixels or less. ...
doi:10.3390/jpm12122022
pmid:36556243
pmcid:PMC9784641
fatcat:gmu5ishnufauxhgt3qbownrafi
« Previous
Showing results 1 — 15 out of 519 results