Useful Links
Computer Science
Computer Vision
Computer Vision
1. Introduction to Computer Vision
2. Digital Image Fundamentals
3. Image Processing and Enhancement
4. Feature Detection and Description
5. Image Segmentation
6. Camera Geometry and 3D Vision
7. Motion Analysis and Video Processing
8. Classical Machine Learning for Vision
9. Deep Learning for Computer Vision
10. Core Vision Tasks with Deep Learning
11. Advanced Computer Vision Topics
12. Implementation and Practical Considerations
13. Ethics and Societal Impact
Core Vision Tasks with Deep Learning
Image Classification
Problem Formulation
Single-Label Classification
Multi-Label Classification
Hierarchical Classification
Network Architectures
Standard CNN Architectures
Attention Mechanisms
Vision Transformers
Evaluation Metrics
Top-1 Accuracy
Top-k Accuracy
Mean Average Precision
Advanced Techniques
Few-Shot Learning
Zero-Shot Learning
Domain Adaptation
Object Detection
Problem Definition
Localization vs Detection
Bounding Box Representation
Multi-Object Detection
Two-Stage Detectors
R-CNN Family
R-CNN
Fast R-CNN
Faster R-CNN
Region Proposal Networks
Feature Pyramid Networks
Single-Stage Detectors
YOLO Family
YOLOv1 through YOLOv8
Architecture Evolution
SSD
Multi-Scale Detection
Default Boxes
RetinaNet
Focal Loss
Feature Pyramid Networks
Detection Components
Anchor Generation
Bounding Box Regression
Non-Maximum Suppression
Hard Negative Mining
Evaluation Metrics
Average Precision
Mean Average Precision
Intersection over Union
Semantic Segmentation
Problem Formulation
Pixel-Level Classification
Dense Prediction
Network Architectures
Fully Convolutional Networks
Encoder-Decoder Structure
Skip Connections
U-Net
Biomedical Applications
Symmetric Architecture
DeepLab Family
Atrous Convolution
Spatial Pyramid Pooling
CRF Post-Processing
PSPNet
Pyramid Scene Parsing
Global Context
Advanced Techniques
Multi-Scale Processing
Attention Mechanisms
Boundary Refinement
Evaluation Metrics
Pixel Accuracy
Mean IoU
Frequency Weighted IoU
Instance Segmentation
Problem Definition
Object Detection plus Segmentation
Instance-Level Masks
Mask R-CNN
Architecture Overview
Mask Branch
RoIAlign Operation
Alternative Approaches
YOLACT
SOLOv2
Panoptic FPN
Panoptic Segmentation
Stuff and Things
Unified Framework
Evaluation Metrics
Average Precision for Masks
Panoptic Quality
Image Generation
Generative Models Overview
Discriminative vs Generative
Likelihood-Based Models
Implicit Models
Variational Autoencoders
Encoder-Decoder Architecture
Latent Space Representation
Variational Inference
Reparameterization Trick
Generative Adversarial Networks
Generator Network
Discriminator Network
Adversarial Training
Training Instabilities
GAN Variants
DCGAN
StyleGAN
CycleGAN
Pix2Pix
Diffusion Models
Forward Diffusion Process
Reverse Diffusion Process
Denoising Diffusion Probabilistic Models
Score-Based Models
Applications
Image Synthesis
Image-to-Image Translation
Super-Resolution
Inpainting
Previous
9. Deep Learning for Computer Vision
Go to top
Next
11. Advanced Computer Vision Topics