IoU (Intersection over Union) in Computer Vision - Model Pipeline Trace

Model Pipeline - IoU (Intersection over Union)

This pipeline calculates the Intersection over Union (IoU) metric to measure how well predicted bounding boxes match the true boxes in object detection tasks.

Data Flow - 4 Stages

1Input bounding boxes

N predicted boxes and N true boxes→Receive predicted and true bounding boxes coordinates→N predicted boxes and N true boxes

Predicted box: [x1=30, y1=40, x2=70, y2=80], True box: [x1=50, y1=60, x2=90, y2=100]

↓

2Calculate intersection

N predicted boxes and N true boxes→Find overlapping area between predicted and true boxes→N intersection areas

Intersection box: [x1=50, y1=60, x2=70, y2=80], area=400

↓

3Calculate union

N predicted boxes and N true boxes→Calculate total area covered by both boxes minus intersection→N union areas

Union area = predicted area + true area - intersection area = 1600 + 1600 - 400 = 2800

↓

4Compute IoU

N intersection areas and N union areas→Divide intersection area by union area for each box pair→N IoU scores between 0 and 1

IoU = 400 / 2800 = 0.1429

Training Trace - Epoch by Epoch

Loss
1.0 |***************
0.8 |************  
0.6 |********     
0.4 |******       
0.2 |***          
0.0 +------------
     1 2 3 4 5 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.75	0.40	Initial IoU scores are low, model starts learning bounding box locations
2	0.60	0.55	IoU improves as predicted boxes better overlap true boxes
3	0.45	0.70	Model predicts bounding boxes closer to ground truth, IoU increases
4	0.35	0.80	Good overlap achieved, IoU scores near 0.8 on average
5	0.30	0.85	Model converges with high IoU, bounding boxes well aligned

Prediction Trace - 4 Layers

Layer 1: Input predicted and true boxes

Layer 2: Calculate intersection box

Layer 3: Calculate union area

Layer 4: Compute IoU score

Model Quiz - 3 Questions

What does a higher IoU score indicate about predicted and true bounding boxes?

A They are farther apart

B They overlap more closely

C They have no overlap

D They have the same area

Key Insight

IoU is a key metric in object detection that quantifies how well predicted boxes match true boxes by measuring their overlap. Higher IoU means better predictions and is used to guide model training and evaluation.