AI |
Artificial Intelligence |
AP |
Average Precision |
CA |
Coordinate-Attention |
CAM |
Channel Attention Mechanism |
CBAM |
Convolutional Block Attention Module |
CCA |
Coordinate-Channel Attention |
CE |
Cross-Entropy |
CIoU |
Complete Intersection-over-Union |
CNN |
Convolutional Neural Network |
COCO |
Common Objects in Context |
CPU |
Central Process Unit |
CSA |
Coordinate-Spatial Attention |
CSP |
Cross Stage Partial |
CV |
Computer Vision |
DIoU |
Distance Intersection-over-Union |
DL |
Deep Learning |
DNN |
Deep Neural Network |
DOTA |
Dataset for Object Detection in Aerial images |
FPN |
Feature Pyramid Network |
FPS |
Frames Per Second |
GIoU |
Generalized Intersection-over-Union |
GPU |
Graphics Processing Unit |
GT |
Ground-Truth |
HSV |
Hue, Saturation and Value |
IoU |
Intersection-over-Union |
mAP |
Mean Average Precision |
ML |
Machine Learning |
OTA |
Optimal Transport Assignment |
PAN |
Path Aggregation Network |
RPN |
Region Proposal Network |
SAM |
Spatial Attention Mechanism |
SE |
Squeeze-and-Excitation |
SENet |
Squeeze-and-Excitation Network |
SimAM |
Simple Parameter-free Attention Module |
SimOTA |
Simplified Optimal Transport Assignment |
SoTA |
State-of-the-Art |
VOC |
Visual Object Classes |
YOLO |
You Only Look Once |