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
Residual Convolutional Neural Network Revisited with Active Weighted Mapping
[article]
2018
arXiv
pre-print
Preserved Fulltext
It results in multiple paths of data flow under a network and the paths are merged with the equal weights. ...
In this paper, we introduce the active weighted mapping method which infers proper weight values based on the characteristic of input data on the fly. ...
Introduction It has recently been noted that deeper stacking of the layers of a convolutional neural network lead to better accuracy of the visual recognition. ...
arXiv:1811.06878v1
fatcat:onyaea26yret7nkjwplhfpslpa
DVMN: Dense Validity Mask Network for Depth Completion
[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.
We develop a guided convolutional neural network focusing on gathering dense and valid information from sparse depth maps. ...
State of the art methods use image guided neural networks for dense depth completion. ...
Current state of the art solutions rely on neural networks to complete depth maps. ...
arXiv:2107.06709v1
fatcat:sykaqvo7sngdblfkgavqfdeedi
Camera-Based Blind Spot Detection with a General Purpose Lightweight Neural Network
2019
Electronics
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.
Many new convolutional neural network (CNN) structures have been proposed and most of the networks are very deep in order to achieve the state-of-art performance when evaluated with benchmarks. ...
Subsequently, a series of experiments are conducted to design an efficient neural network by comparing some of the latest deep learning models. ...
The extreme case for weight representation is the binary notation. Some researchers directly applied binary weights or activations during the model training process [28, 29] . ...
doi:10.3390/electronics8020233
fatcat:le3byzn2h5axrekdzwbii5h6im
Deep Anchored Convolutional Neural Networks
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
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.
We name it Deep Anchored Convolutional Neural Network (DACNN). ...
Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks. ...
Conclusion We introduced a new convolutional neural network architecture, which we refer it as Deep Anchored Convolutional Neural Network (DACNN). ...
doi:10.1109/cvprw.2019.00089
dblp:conf/cvpr/HuangDR19
fatcat:ozr6po45kjcplcmv7d3qzso76m
Deep Anchored Convolutional Neural Networks
[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 2019; you can also visit the original URL.
The file type is application/pdf.
We name it Deep Anchored Convolutional Neural Network (DACNN). ...
Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks. ...
Conclusion We introduced a new convolutional neural network architecture, which we refer it as Deep Anchored Convolutional Neural Network (DACNN). ...
arXiv:1904.09764v1
fatcat:6hksfylrzzbf7bwedjwdwyj4vy
Perturbative Neural Networks
2018
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
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.
Empirically, deep neural networks with perturbation layers, called Perturbative Neural Networks (PNNs), in lieu of convolutional layers perform comparably with standard CNNs on a range of visual datasets ...
The perturbation layer does away with convolution in the traditional sense and instead computes its response as a weighted linear combination of non-linearly activated additive noise perturbed inputs. ...
Networks with binary weights [3, 2, 23] , networks with sparse convolutional weights [20, 21, 18] , networks with efficient factorization of the convolutional weights [10, 15] and networks with a hybrid ...
doi:10.1109/cvpr.2018.00349
dblp:conf/cvpr/Juefei-XuBS18
fatcat:4r35f3ppprb4phabfgfjhcj2ta
Denoising single images by feature ensemble revisited
[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.
The proposed architecture's number of parameters remains smaller than the number for most of the previous networks and still achieves significant improvements over the current state-of-the-art networks ...
The proposed architecture revisits the concept of modular concatenation instead of long and deeper cascaded connections, to recover a cleaner approximation of the given image. ...
These modules are standing upon the customized convolution and residual setup with supportive activation functions. ...
arXiv:2207.05176v1
fatcat:k5ve53ppojcntkwlnn2mhzj53e
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
[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.
Other Versions
CNN network by forcing it to mimic the attention maps of a powerful teacher network. ...
To that end, we propose several novel methods of transferring attention, showing consistent improvement across a variety of datasets and convolutional neural network architectures. ...
Visualizing attention maps in deep convolutional neural networks is an open problem. ...
arXiv:1612.03928v3
fatcat:vz5we7vsrbhatjrq723jobandy
Dilated Deep Residual Network for Image Denoising
[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.
Other Versions
Variations of deep neural networks such as convolutional neural network (CNN) have been successfully applied to image denoising. ...
Specifically, we enlarge receptive field by adopting dilated convolution in residual network, and the dilation factor is set to a certain value. ...
Variations of deep neural networks such as convolutional neural network (CNN) have been successfully applied to image denoising [5] , [6] . ...
arXiv:1708.05473v3
fatcat:zrws7qe7jjbyre37kakd5ogcoi
Spatial Channel Attention for Deep Convolutional Neural Networks
2022
Mathematics
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.
The proposed attention mechanism can be seamlessly integrated into any convolutional neural network since it is a lightweight general module. ...
Recently, the attention mechanism combining spatial and channel information has been widely used in various deep convolutional neural networks (CNNs), proving its great potential in improving model performance ...
neural networks (CNNs). ...
doi:10.3390/math10101750
fatcat:lluoelwotve77hfrsfmc5cdg4m
Sparsely Aggregated Convolutional Networks
[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.
We explore a key architectural aspect of deep convolutional neural networks: the pattern of internal skip connections used to aggregate outputs of earlier layers for consumption by deeper layers. ...
This is a primary reason for the widespread adoption of residual networks, which aggregate outputs via cumulative summation. ...
Highway Networks [14] and ResNets [6] create shortcut connections between layers with an identity mapping and are among the first works that successfully trained convolutional neural networks with ...
arXiv:1801.05895v1
fatcat:saasbivlhjanpo62y2nso745vy
Performance Guaranteed Network Acceleration via High-Order Residual Quantization
[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.
In particular, the proposed scheme recursively performs residual quantization and yields a series of binary input images with decreasing magnitude scales. ...
Input binarization has shown to be an effective way for network acceleration. ...
The idea of BWN is to constrain a convolutional neural network with binary weights. ...
arXiv:1708.08687v1
fatcat:cv2csvlwbbanjmzu3mgwnehgku
Neural Networks for Lorenz Map Prediction: A Trip Through Time
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:1903.07768v4 fatcat:dvttdh24l5gr5akdcldswltvluOther Versions
The article is a reflection upon the evolution of neural networks with respect to the prediction performance on this canonical task. ...
In this article the Lorenz dynamical system is revived and revisited and the current state of the art results for one step ahead forecasting for the Lorenz trajectories are published. ...
In the convolutional neural network case the objective includes the term corresponding to the l2 penalty on the weights as well. ...
arXiv:1903.07768v5
fatcat:r6ey47umtjc7hnulqai23c66sm
Widening and Squeezing: Towards Accurate and Efficient QNNs
[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.
Other Versions
Then, a compact quantization neural network but with sufficient representation ability will be established. ...
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision ...
Wherein, binary neural networks with weights and activations constrained to +1 or −1 have many advantages. ...
arXiv:2002.00555v2
fatcat:cfksfi7yg5cyxocragvccdf25a
Perturbative Neural Networks
[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.
Empirically, deep neural networks with perturbation layers, called Perturbative Neural Networks (PNNs), in lieu of convolutional layers perform comparably with standard CNNs on a range of visual datasets ...
The perturbation layer does away with convolution in the traditional sense and instead computes its response as a weighted linear combination of non-linearly activated additive noise perturbed inputs. ...
Networks with binary weights [3, 2, 23] , networks with sparse convolutional weights [20, 21, 18] , networks with efficient factorization of the convolutional weights [10, 15] and networks with a hybrid ...
arXiv:1806.01817v1
fatcat:fbxfwepy2ferjaszofn2igojvy
« Previous
Showing results 1 — 15 out of 2,493 results