M12.4 CONNECT THE MECHANISM
Locate objects and label their pixels
To blur a stranger's face, "there's a face in this photo" isn't enough. Learn how models draw boxes, remove duplicates, score themselves, and color in exact pixels.
LESSON OVERVIEW14 min lesson
Lesson overview
To blur a stranger's face, "there's a face in this photo" isn't enough. Learn how models draw boxes, remove duplicates, score themselves, and color in exact pixels.
What you’ll explore
- Detection predicts object instances and locations, segmentation assigns pixel-level structure, and tracking connects instances over time; each needs task-specific matching and metrics.
GO TO THE SOURCE
Original explanations, connected to the research.
Dive into Deep Learning — object detection and bounding boxesYou Only Look Once: Unified, Real-Time Object Detection (Redmon et al., 2015)Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (Ren et al., 2015)U-Net: Convolutional Networks for Biomedical Image Segmentation (Ronneberger, Fischer & Brox, 2015)Mask R-CNN (He, Gkioxari, Dollár & Girshick, 2017)Segment Anything (Kirillov et al., 2023)Suggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.