Buchumschlag

Advanced Research and Applications of Deep Learning and Neural Network in Image Recognition

This reprint aims to immerse the reader in the latest research and applications of deep learning and neural networks in image recognition. Deep learning algorithms are the major driving force behind recent advances in image classification. The success of deep learning is powered by two crucial issue...

Ausführliche Beschreibung

Gespeichert in:
Format: Online
Sprache:Englisch
Veröffentlicht: MDPI - Multidisciplinary Digital Publishing Institute 2024
Schlagworte:
multi-scale residual group attention
U-Net
smoke segmentation
global information
residential area extraction
mapping requirement
contour regularization
end-to-end deep model
Tian-Hui 1 satellite images
quadrupeds
pose estimation
HRNet network
gait parameters
cyclic federated learning
non-IID
distribution information sharing
knowledge distillation
chamfer distance
convolutional neural network
face verification
Siamese network
head pose estimation
architecture improvement
dynamic channel pruning
memory access improvement
Generalized Zero-Shot Learning
discriminative
semantic-relevant
image classification
partially-shared multi-task learning
transferable representation
deep learning
3D object detection
lidar point cloud
transformer
MobileNetV3
morphological algorithm
railway extraction
aerial imagery
polarization direction measurement
CNN
global average pooling
algorithm
image stitching
image unmixing
in-screen fingerprint recognition
OLED
n/a
thema EDItEUR::J Society and Social Sciences::JH Sociology and anthropology::JHB Sociology::JHBA Social theory
Online-Zugang:ONIX_20240514_9783725804238_283
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
Zusammenfassung:This reprint aims to immerse the reader in the latest research and applications of deep learning and neural networks in image recognition. Deep learning algorithms are the major driving force behind recent advances in image classification. The success of deep learning is powered by two crucial issues: large-scale training datasets and powerful computational platforms. In most cases, the performances obtained by deep neural networks are much better than those of hand-crafted delicate image features. Yet, despite the great success of deep learning in image recognition, numerous challenges remain. This Special Issue aims to present new solutions to these challenging problems.

Ähnliche Einträge