UsefulLinks
Computer Science
Artificial Intelligence
Deep Learning
Deep Learning for Computer Vision
1. Foundations of Computer Vision and Deep Learning
2. Convolutional Neural Networks
3. Training Deep Vision Models
4. Classical CNN Architectures
5. Modern CNN Architectures
6. Core Computer Vision Tasks
7. Advanced Topics and Applications
8. Practical Implementation and Deployment
5.
Modern CNN Architectures
5.1.
Efficient Architectures
5.1.1.
MobileNet v1
5.1.1.1.
Depthwise Separable Convolutions
5.1.1.2.
Width Multiplier
5.1.1.3.
Resolution Multiplier
5.1.2.
MobileNet v2
5.1.2.1.
Inverted Residuals
5.1.2.2.
Linear Bottlenecks
5.1.3.
MobileNet v3
5.1.3.1.
Neural Architecture Search
5.1.3.2.
Squeeze-and-Excitation
5.1.4.
EfficientNet
5.1.4.1.
Compound Scaling
5.1.4.2.
Model Scaling Dimensions
5.1.4.3.
EfficientNet Family
5.1.5.
ShuffleNet
5.1.5.1.
Channel Shuffle Operation
5.1.5.2.
Group Convolutions
5.2.
Attention-based Architectures
5.2.1.
Squeeze-and-Excitation Networks
5.2.1.1.
Channel Attention
5.2.1.2.
Global Information
5.2.2.
Convolutional Block Attention Module
5.2.2.1.
Channel and Spatial Attention
5.2.3.
Non-local Networks
5.2.3.1.
Self-attention in CNNs
5.2.3.2.
Long-range Dependencies
5.3.
Neural Architecture Search
5.3.1.
Search Space Design
5.3.2.
Search Strategy
5.3.3.
Performance Estimation
5.3.4.
DARTS
5.3.4.1.
Differentiable Architecture Search
5.3.5.
ProxylessNAS
5.3.5.1.
Direct Hardware Optimization
Previous
4. Classical CNN Architectures
Go to top
Next
6. Core Computer Vision Tasks