Phase 1: Convolutional Neural Networks · ~75 minutes · Python

Instance Segmentation — Mask R-CNN

Add a tiny mask branch to a Faster R-CNN detector and you have instance segmentation. The hard part is RoIAlign, and it is harder than it looks.

What you will learn

Trace the Mask R-CNN architecture end-to-end: backbone, FPN, RPN, RoIAlign, box head, mask head
Implement RoIAlign from scratch and explain why RoIPool is no longer used
Use the torchvision `maskrcnn_resnet50_fpn_v2` pretrained model for production-quality instance masks and read its output format correctly
Fine-tune Mask R-CNN on a small custom dataset by replacing the box and mask heads and keeping the backbone frozen

Introduction

Type: Build + Learn
Languages: Python
Prerequisites: Object Detection — YOLO from Scratch, Semantic Segmentation — U-Net
Time: ~75 minutes

Objective

Learning objectives

Trace the Mask R-CNN architecture end-to-end: backbone, FPN, RPN, RoIAlign, box head, mask head
Implement RoIAlign from scratch and explain why RoIPool is no longer used
Use the torchvision maskrcnn_resnet50_fpn_v2 pretrained model for production-quality instance masks and read its output format correctly
Fine-tune Mask R-CNN on a small custom dataset by replacing the box and mask heads and keeping the backbone frozen

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.