Fully convolutional neural nets in-the-wild [PDF]
Remote Sensing Letters, 2020 The ground breaking performance of fully convolutional neural nets (FCNs) for semantic segmentation tasks has yet to be achieved for landcover classification, partly because a lack of suitable training data.
D. Simms
semanticscholar +4 more sources
CE-Dedup: Cost-Effective Convolutional Neural Nets Training based on Image Deduplication [PDF]
2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/SocialCom/SustainCom), 2021 Attributed to the ever-increasing large image datasets, Convolutional Neural Networks (CNNs) have become popular for vision-based tasks. It is generally admirable to have larger-sized datasets for higher network training accuracies.
Xuan Li, Liqiong Chang, Xue Liu
semanticscholar +5 more sources
Convolutional neural nets for estimating the run time and energy consumption of the sparse matrix-vector product [PDF]
The international journal of high performance computing applications, 2020 Modeling the performance and energy consumption of the sparse matrix-vector product (SpMV) is essential to perform off-line analysis and, for example, choose a target computer architecture that delivers the best performance-energy consumption ratio ...
M. Barreda +2 more
openalex +2 more sources
Simplicial 2-Complex Convolutional Neural Nets
, 2020 Recently, neural network architectures have been developed to accommodate when the data has the structure of a graph or, more generally, a hypergraph. While useful, graph structures can be potentially limiting. Hypergraph structures in general do not account for higher order relations between their hyperedges. Simplicial complexes offer a middle ground,
Eric Bunch +3 more
openalex +4 more sources
Video Anomaly Detection Using Pre-Trained Deep Convolutional Neural Nets and Context Mining [PDF]
ACS/IEEE International Conference on Computer Systems and Applications, 2020 Anomaly detection is critically important for intelligent surveillance systems to detect in a timely manner any malicious activities. Many video anomaly detection approaches using deep learning methods focus on a single camera video stream with a fixed ...
Chongke Wu +3 more
semanticscholar +5 more sources
SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud [PDF]
IEEE International Conference on Robotics and Automation, 2017 We address semantic segmentation of road-objects from 3D LiDAR point clouds. In particular, we wish to detect and categorize instances of interest, such as cars, pedestrians and cyclists.
Bichen Wu +3 more
openalex +3 more sources
Inferring depth contours from sidescan sonar using convolutional neural nets [PDF]
IET radar, sonar & navigation, 2019 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
openalex +2 more sources
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks [PDF]
European Conference on Computer Vision, 2016 We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32\(\times \) memory saving.
Mohammad Rastegari +3 more
semanticscholar +3 more sources
Farm Detection based on Deep Convolutional Neural Nets and Semi-supervised Green Texture Detection using VIS-NIR Satellite Image [PDF]
International Conference on Data Technologies and Applications, 2019 Farm detection using low resolution satellite images is an important topic in digital agriculture. However, it has not received enough attention compared to high-resolution images.
Sara Sharifzadeh, Jagati Tata, Bo Tan
openalex +2 more sources
DeepSat V2: feature augmented convolutional neural nets for satellite image classification [PDF]
Remote Sensing Letters, 2019 Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches are
Qun Liu +6 more
openalex +3 more sources