Results 21 to 30 of about 54,400 (268)
Convolutional Neural Networks using FPGA-based Pipelining
Iraqi Journal for Computer Science and Mathematics, 2023 In order to speed up convolutional neural networks (CNNs), this study gives a complete overview of the use of FPGA-based pipelining for hardware acceleration of CNNs.
Gheni A. Ali, ahmed hussein ali
doaj +1 more source
Diagnostics, 2022 (1) Background: The present study aims to evaluate and compare the model performances of different convolutional neural networks (CNNs) used for classifying sagittal skeletal patterns.
Haizhen Li +4 more
doaj +1 more source
Proceedings of the 2021 Great Lakes Symposium on VLSI, 2021 Memory bandwidth utilization has become the key performance bottleneck for state-of-the-art variants of neural network kernels. Current structures such as depth-wise, point-wise and atrous convolutions have already introduced diverse and discontinuous memory access patterns, which impact efficient activation supply due to more frequent cache misses and
Zheng Wang +12 more
openaire +1 more source
Evaluation of the benchmark datasets for testing the efficacy of deep convolutional neural networks
Visual Informatics, 2021 In the past decade, deep neural networks, and specifically convolutional neural networks (CNNs), have been becoming a primary tool in the field of biomedical image analysis, and are used intensively in other fields such as object or face recognition ...
Sanchari Dhar, Lior Shamir
doaj +1 more source
P-CNN: Pose-Based CNN Features for Action Recognition [PDF]
2015 IEEE International Conference on Computer Vision (ICCV), 2015 ICCV, December 2015, Santiago ...
Chéron, Guilhem +2 more
openaire +3 more sources
Adaptive Deep Learning for Soft Real-Time Image Classification
Technologies, 2021 CNNs (Convolutional Neural Networks) are becoming increasingly important for real-time applications, such as image classification in traffic control, visual surveillance, and smart manufacturing.
Fangming Chai, Kyoung-Don Kang
doaj +1 more source
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017 We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with
Kaiming He +3 more
openaire +4 more sources
Remote Sensing, 2017 Deep convolutional neural networks (CNNs) have been widely used to obtain high-level representation in various computer vision tasks. However, in the field of remote sensing, there are not sufficient images to train a useful deep CNN. Instead, we tend to
Jie Wang +4 more
doaj +1 more source
Journal of Marine Science and Engineering, 2021 To meet the increasing sailing demand of the Northeast Passage of the Arctic, a daily prediction model of sea ice concentration (SIC) based on the convolutional long short-term memory network (ConvLSTM) algorithm was proposed in this study.
Quanhong Liu +4 more
doaj +1 more source
FEBS Open Bio, EarlyView.In this study, we developed a deep learning method for mitotic figure counting in H&E‐stained whole‐slide images and evaluated its prognostic impact in 13 external validation cohorts from seven different cancer types. Patients with more mitotic figures per mm2 had significantly worse patient outcome in all the studied cancer types except colorectal ...
Joakim Kalsnes +32 more
wiley +1 more source