Core

Computer Vision: Classification, Detection, Segmentation

Vision tasks form a ladder of increasing spatial precision: classification labels the whole image, detection draws bounding boxes around objects, semantic segmentation labels every pixel by class, and instance segmentation separates individual objects pixel by pixel. Each has its own output format and metric (top-1 accuracy, mAP at IoU thresholds), and CNNs versus vision transformers trade off differently across them.

a free account unlocks the core curriculum tier · no card

RELATED CONCEPTS

Overfitting and Regularization The Transformer, Intuitively Precision, Recall and F1

PRACTICE THIS IN REAL QUESTIONS

ML System Design (Product)Design a landmark or image recognition system at scale.→Machine Learning & Data ScienceA customer wants to segment 2 million users. Walk me through clustering, k-means, choosing k, and where it goes wrong.→Machine Learning & Data ScienceExplain CNN fundamentals (convolution, pooling, parameter sharing). When does classical computer vision still matter?→System Design & Production EngineeringDesign a real-time radiology copilot that flags regions and drafts a report in under 2 seconds at 10 studies/sec, recall first.→