Results 271 to 280 of about 5,636 (303)

Inferring depth contours from sidescan sonar using convolutional neural nets

IET Radar, Sonar and Navigation, 2020
Sidescan sonar images are 2D representations of the seabed. The pixel location encodes distance from the sonar and along track coordinate. Thus one dimension is lacking for generating bathymetric maps from sidescan.
Yiping Xie, Nils Bore, John Folkesson
exaly   +2 more sources

Some of the next articles are maybe not open access.

Related searches:

KNOWLEDGE TRANSFER IN DEEP CONVOLUTIONAL NEURAL NETS

International Journal on Artificial Intelligence Tools, 2008
Knowledge transfer is widely held to be a primary mechanism that enables humans to quickly learn new complex concepts when given only small training sets. In this paper, we apply knowledge transfer to deep convolutional neural nets, which we argue are particularly well suited for knowledge transfer. Our initial results demonstrate that components of a
Steven Gutstein, Olac Fuentes, Eric Freudenthal   +2 more
openaire   +2 more sources

Wavelet J-Net: A Frequency Perspective on Convolutional Neural Networks

2021 International Joint Conference on Neural Networks (IJCNN), 2021
It is well acknowledged in image processing domain that the information can be decomposed into different frequency parts and each part has its own merits. However, existing neural networks always ignore the distinctions and straightforwardly feed all the information into neural networks together, treating them equally. In this paper, we propose a novel
Linfeng Zhang 0001, Xiaoman Zhang, Chenglong Bao, Kaisheng Ma   +3 more
openaire   +1 more source

Convolutional neural net bagging for online visual tracking

Computer Vision and Image Understanding, 2016
The proposed CNN bagging method is simple yet effective.It addresses the label noise and model uncertainty problems simultaneously for CNN-based trackers.The state-of-the-art performances on 3 recent benchmarks i.e., CVPR2013, VOT2013 and TB50 illustrate the validity of the proposed algorithm.
Hanxi Li, Yi Li 0025, Fatih Porikli
openaire   +1 more source

Pulse-Net: Dynamic Compression of Convolutional Neural Networks

2019 IEEE 5th World Forum on Internet of Things (WF-IoT), 2019
Convolutional Neural Networks (CNNs) are used in a range of computer vision tasks, with state-of-the-art CNNs such as AlexNet and VGG16 constructed using a large number of parameter and multiply-add operations (MACs). These tasks require high computational power and high energy requirements to run the CNNs, making them unsuitable for deployment on In ...
David Browne, Michael Giering, Steven D. Prestwich   +2 more
openaire   +1 more source

W–net: A Convolutional Neural Network for Retinal Vessel Segmentation

2021
In this paper we propose a method for retinal vessel segmentation based on a multi-stage deep convolutional neural network with short connections. The proposed method is a two-stage application of an improved U–net architecture. In the first stage, a probability score for the vascular structure presence is computed from a set of random patches taken ...
Alan Reyes-Figueroa, Mariano Rivera
openaire   +1 more source

U-Net Based Convolutional Neural Network for Skeleton Extraction

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019
Skeletonization is a process aimed to extract a line-like object shape representation, skeleton, which is of great interest for optical character recognition, shape-based object matching, recognition, biomedical image analysis, etc.. Existing methods for skeleton extraction are typically based on topological, morphological or distance transform and are
Oleg Panichev, Alona Voloshyna
openaire   +1 more source

Elasto-Net: An HDL Conversion Framework For Convolutional Neural Networks

2018 52nd Asilomar Conference on Signals, Systems, and Computers, 2018
Hardware solutions for Convolutional Neural Networks (CNN) have emerged in the recent wake of their success in image classification. Although CNNs are effective in classifying images, they can be highly complex to implement in hardware. CNNs come in many shapes and sizes.
Anaam Ansari, Tokunbo Ogunfunmi
openaire   +1 more source

AMI-Net: Convolution Neural Networks With Affine Moment Invariants

IEEE Signal Processing Letters, 2018
Affine moment invariant (AMI) is a kind of hand-crafted image feature, which is invariant to affine transformations. This property is precisely what the standard convolution neural network (CNN) is difficult to achieve. In this letter, we present a kind of network architecture to introduce AMI into CNN, which is called AMI-Net.
You Hao, Qi Li, Hanlin Mo, He Zhang 0012, Hua Li 0009   +4 more
openaire   +1 more source

CIASM-Net: A Novel Convolutional Neural Network for Dehazing Image

2020 5th International Conference on Computer and Communication Systems (ICCCS), 2020
When light propagates in the medium such as haze, the image information collected by the imaging sensor is seriously degraded due to the scattering of particles, which greatly limits the application value of the image. In this paper, a novel convolutional neural network model called CIASM-Net is proposed to implement image dehazing.
Wen Qian, Chao Zhou 0007, Dengyin Zhang
openaire   +1 more source