Track 3 · Path · 4 explainers
Computer Vision
Pooling, detection, segmentation, and data augmentation
- 1
Pooling & Downsampling
Reduce spatial dimensions while preserving the most important features in feature maps
- 2
Object Detection
Locate and classify multiple objects in an image using bounding boxes and confidence scores
- 3
Image Segmentation
Classify every pixel in an image — from semantic regions to individual object instances
- 4
Data Augmentation
Artificially expand training data with transformed copies to reduce overfitting