Encoding features from multi-layer Gabor filtering for visual smoke recognition
Sign Up to like & getrecommendations! Published in 2020 at "Pattern Analysis and Applications"
DOI: 10.1007/s10044-020-00864-x
Abstract: It is a challenging task to accurately recognize smoke from visual scenes due to large variations in smoke shape, color and texture. To improve recognition accuracy, we propose a framework mainly with a robust local… read more here.
Keywords: feature maps; feature; smoke; gabor convolutional ... See more keywords
Pedestrian detection based on multi-convolutional features by feature maps pruning
Sign Up to like & getrecommendations! Published in 2017 at "Multimedia Tools and Applications"
DOI: 10.1007/s11042-017-4837-0
Abstract: Convolutional neural network (CNN) has developed such a large network size in last few years, so reducing the storage requirement without hurting its accuracy becomes necessary. In this paper, in order to reduce the number… read more here.
Keywords: feature maps; feature; based multi; pedestrian detection ... See more keywords
Recurrent convolutions of binary-constraint Cellular Neural Network for texture recognition
Sign Up to like & getrecommendations! Published in 2020 at "Neurocomputing"
DOI: 10.1016/j.neucom.2019.12.119
Abstract: Abstract Texture recognition is one of the most important branches in image research. This paper mainly aims to develop a new solution to address texture recognition using a Cellular Neural Network (CellNN). Firstly, it proposes… read more here.
Keywords: feature maps; feature; texture recognition; neural network ... See more keywords
ESSN: Enhanced Semantic Segmentation Network by Residual Concatenation of Feature Maps
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.2969442
Abstract: Semantic segmentation performs pixel-level classification of multiple classes in the input image. Previous studies on semantic segmentation have used various methods such as multi-scale image, encoder-decoder, attention, spatial pyramid pooling, conditional random field, and generative… read more here.
Keywords: segmentation network; semantic segmentation; feature maps; segmentation ... See more keywords
CSANet: Channel and Spatial Mixed Attention CNN for Pedestrian Detection
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Access"
DOI: 10.1109/access.2020.2986476
Abstract: Current mainstream pedestrian detectors tend to profit directly from convolutional neural networks (CNNs) that are designed for image classification. While requiring a large downsampling factor to produce high-level semantic features, CNNs cannot adaptively focus on… read more here.
Keywords: channel spatial; attention; feature maps; pedestrian detection ... See more keywords
Adversarial Attack Using Sparse Representation of Feature Maps
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3222531
Abstract: Deep neural networks can be fooled by small imperceptible perturbations called adversarial examples. Although these examples are carefully crafted, they involve two major concerns. In some cases, adversarial examples generated are much larger than minimal… read more here.
Keywords: adversarial examples; feature; adversarial attack; feature maps ... See more keywords
An Efficient Deep Unsupervised Superresolution Model for Remote Sensing Images
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"
DOI: 10.1109/jstars.2020.2984589
Abstract: Superresolution (SR) has provided an effective solution to the increasing need for high-resolution images in remote sensing applications. Among various SR methods, deep learning-based SR (DLSR) has made a significant breakthrough. However, supervised DLSR methods… read more here.
Keywords: computational burden; remote sensing; superresolution; model ... See more keywords
A Fast and Compact 3-D CNN for Hyperspectral Image Classification
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Geoscience and Remote Sensing Letters"
DOI: 10.1109/lgrs.2020.3043710
Abstract: Hyperspectral images (HSIs) are used in a large number of real-world applications. HSI classification (HSIC) is a challenging task due to high interclass similarity, high intraclass variability, overlapping, and nested regions. The 2-D convolutional neural… read more here.
Keywords: compact cnn; cnn hyperspectral; fast compact; feature maps ... See more keywords
An Efficient Axial-Attention Network for Video-Based Person Re-Identification
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2022.3178673
Abstract: The Non-local self-attention mechanism can significantly improve the capability of feature representation with long-range dependencies at the cost of high computational complexity. To address the issue, the self-attention-based autoregressive axial transformer has been proposed to… read more here.
Keywords: network; efficient axial; feature maps; axial attention ... See more keywords
FCHP: Exploring the Discriminative Feature and Feature Correlation of Feature Maps for Hierarchical DNN Pruning and Compression
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Circuits and Systems for Video Technology"
DOI: 10.1109/tcsvt.2022.3170620
Abstract: Pruning can remove the redundant parameters and structures of Deep Neural Networks (DNNs) to reduce inference time and memory overhead. As one of the important components of DNN, feature maps (FMs) have been widely used… read more here.
Keywords: feature; discriminative feature; feature correlation; feature maps ... See more keywords
Unsupervised Change Detection Using Convolutional-Autoencoder Multiresolution Features
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2022.3140404
Abstract: The use of deep learning (DL) methods for change detection (CD) is currently dominated by supervised models that require a large number of labeled samples. However, these samples are difficult to acquire in the multitemporal… read more here.
Keywords: change detection; feature maps; convolutional autoencoder; multiresolution ... See more keywords