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
Object Detection in UAV Images via Global Density Fused Convolutional Network
2020
Remote Sensing
Preserved Fulltext
To address the above issues, we propose a novel global density fused convolutional network (GDF-Net) optimized for object detection in UAV images. ...
The presented GDF-Net framework can be instantiated to not only the base networks selected in this study but also other popular object detection models. ...
Different from early algorithms by selected features and background information, the deep learning based approaches automate object detection in UAV images and are transferable to different datasets. ...
doi:10.3390/rs12193140
fatcat:pw6ynhfd7fejhcijibrlixv6se
Special Section Guest Editorial: Feature and Deep Learning in Remote Sensing Applications
2018
Journal of Applied Remote Sensing
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 2018; you can also visit the original URL.
The file type is application/pdf.
Most articles used or extended convolutional neural networks (CNNs) and were application oriented, with a few providing new deep learning models and modules. ...
A common theme encountered was the use of nonremote sensing pretrained networks and transfer learning. ...
Marcum et al. in "Rapid broad area search and detection of Chinese surface-to-air missile sites using deep convolutional neural networks" put forth a deep CNN-based chip detection followed by spatial clustering ...
doi:10.1117/1.jrs.11.042601
fatcat:pq3xg2sggfdtljjs3hrmp7tzdm
Deep Reasoning with Multi-Scale Context for Salient Object Detection
[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
To detect salient objects accurately, existing methods usually design complex backbone network architectures to learn and fuse powerful features. ...
Such a deep inference module, though with simple architecture, can directly perform reasoning about salient objects from the multi-scale convolutional features fast, and give superior salient object detection ...
Recently, convolutional neural networks (CNNs), especially the fully convolutional networks (FCNs), have been extensively utilized to learn more powerful features for salient object detection. ...
arXiv:1901.08362v2
fatcat:esln75k3unfgdphwu43w56hh7m
Video Salient Object Detection via Spatiotemporal Attention Neural Networks
2019
Neurocomputing
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.
However, these deep learning models cannot adapt directly to the video saliency detection, even if transfer learning is introduced into this community. ...
Both of streams are the modified VGG-based FCN, whose convolutional layers are replaced by the dilated ones in the last two convolutional blocks. ...
doi:10.1016/j.neucom.2019.09.064
fatcat:hmmvekkitbhz7ludfmy2fc6k34
WFNet: A Wider and Finer Network for Salient Object Detection
2020
IEEE Access
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.
EDGE-BASED MODELS Many methods based on U-Net architecture have been proposed to detect salient objects [20] [21] [22] . ...
FUSION-BASED MODELS The combination of different features is very effective for salient object detection. ...
doi:10.1109/access.2020.3039890
fatcat:cmyufuveb5c67bz5yvsih6o7t4
Survey on Semantic Segmentation using Deep Learning Techniques
2019
Neurocomputing
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.
Many of these methods have been built using the deep learning paradigm that has shown a salient performance. ...
Second, by providing an overview of the publicly available datasets on which they have been assessed. In addition, we present the common evaluation matrix used to measure their accuracy. ...
, and transfer learning: using pre-trained model as a start point. ...
doi:10.1016/j.neucom.2019.02.003
fatcat:aelsfl7unvdw5j2rtyqhtgqrsm
Autonomous Multiple Tramp Materials Detection in Raw Coal Using Single-Shot Feature Fusion Detector
2021
Applied 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 2021; you can also visit the original URL.
The file type is application/pdf.
In this article, an object detection algorithm based on feature fusion and dense convolutional network is proposed, which is called tramp materials in raw coal single-shot detector (TMRC-SSD), to detect ...
Especially in the detection of small objects, the detection accuracy has increased by 4.1 to 95.57%. ...
On the other hand, the object detection technology based on deep learning improves the performance of the detector by learning from training data and by adaptively extracting stable image resources [14 ...
doi:10.3390/app12010107
fatcat:g6y3h4den5eynk7rqwd2ad4msq
YOLO-DFAN: Effective High-Altitude Safety Belt Detection Network
2022
Future Internet
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 paper proposes the You Only Look Once (YOLO) dependency fusing attention network (DFAN) detection algorithm, improved based on the lightweight network YOLOv4-tiny. ...
In response to the difficulty of extracting the features of an object with a low effective pixel ratio—which is an object with a low ratio of actual area to detection anchor area in the YOLOv4-tiny network—we ...
Deep-learning-based object detection algorithms are primarily divided into two categories: one-and two-stage. ...
doi:10.3390/fi14120349
fatcat:e6detw67xrgifhvzj3vodnuibi
A Review on Multiscale-Deep-Learning Applications
2022
Sensors
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.
In general, most of the existing convolutional neural network (CNN)-based deep-learning models suffer from spatial-information loss and inadequate feature-representation issues. ...
Multiscale representation enables the network to fuse low-level and high-level features from a restricted receptive field to enhance the deep-model performance. ...
In order to utilize an effective transfer-learning-initialization method for these segmentation tasks, it is necessary to apply the dilated convolutions sequentially by adding the specified dilated rate ...
doi:10.3390/s22197384
pmid:36236483
pmcid:PMC9573412
fatcat:g74dirw2nvdudnkrl3atczm2va
Side-Scan Sonar Image Classification Based on Style Transfer and Pre-Trained Convolutional Neural Networks
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Therefore, a side-scan sonar image classification method based on synthetic data and transfer learning is proposed in this paper. ...
neural network pre-trained on ImageNet is introduced for classification. ...
learning machine KNN k-nearest neighbor attractor neural network ...
doi:10.3390/electronics10151823
fatcat:u7tbhjky6rcalnrxmw5qwkdpia
FE-RetinaNet: Small Target Detection with Parallel Multi-Scale Feature Enhancement
2021
Symmetry
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.
), which uses dilated convolution with different expansion rates to avoid multiple down sampling. ...
effect on small targets, with APs increased by 3.2%. ...
Target detection algorithms based on convolutional neural networks can be divided into two categories: one is a two-stage target detection model, such as R-CNN [1] , Fast R-CNN [2] , Faster R-CNN [3 ...
doi:10.3390/sym13060950
fatcat:cs5pnmyoirc3nkmknfjn6pu6sa
An Efficient Object Detection Algorithm Based on Compressed Networks
2018
Symmetry
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.
In recent years, object detection algorithms based on convolutional neural networks have achieved excellent results. ...
By learning the category distribution of the "teacher network", the knowledge of the "teacher network" is refined into a smaller model. ...
Detector mAP (%) Operations (G-Ops) fps (s) Model Size (M) Our Network 72. 6
Conclusions In order to solve the low efficiency problem of object detection algorithms based on convolutional neural ...
doi:10.3390/sym10070235
fatcat:s4c23vnvdfgr5klpxonfiv3lau
FA-YOLO: An Improved YOLO Model for Infrared Occlusion Object Detection under Confusing Background
2021
Wireless Communications and Mobile Computing
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.
Infrared target detection is a popular applied field in object detection as well as a challenge. ...
Firstly, we use GAN to create infrared images from the visible datasets to make sufficient datasets for training as well as using transfer learning. ...
Based on the YOLOv4 model, we used no transfer learning as the comparisons and just train the model on the infrared dataset. 1 . ...
doi:10.1155/2021/1896029
fatcat:5zbcdgftvjboljmhi7bjcduomu
Image Semantic Segmentation Fusion of Edge Detection and AFF Attention Mechanism
2022
Applied 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.
objects, and by 3% for scenes with complex object edges. ...
Deep learning has been widely used in various fields because of its accuracy and efficiency. At present, the improvement of image semantic segmentation accuracy has become the area of most concern. ...
After the training, the model is transplanted to the semantic segmentation network through transfer learning, and the final training of the whole model is completed. ...
doi:10.3390/app122111248
fatcat:ywpl5qxnjbhyrfcrkbtzjgmx4u
Automatic Crack Detection on Road Pavements Using Encoder-Decoder Architecture
2020
Materials
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.
Inspired by the development of deep learning in computer vision and object detection, the proposed algorithm considers an encoder-decoder architecture with hierarchical feature learning and dilated convolution ...
, named U-Hierarchical Dilated Network (U-HDN), to perform crack detection in an end-to-end method. ...
Gao and Mosalam in [51] applied the transfer learning to detect damage images with structural method, and this method can reduce the computational cost by using the pre-trained neural network model. ...
doi:10.3390/ma13132960
pmid:32630713
fatcat:fgubiuizybfw5hsmh7l3ovohnu
« Previous
Showing results 1 — 15 out of 2,954 results