Segmentation evaluation (IoU, Dice) in Computer Vision - Model Pipeline Trace

Model Pipeline - Segmentation evaluation (IoU, Dice)

This pipeline shows how a computer learns to separate objects in images by predicting masks. It then checks how well the predicted masks match the real masks using two scores: IoU and Dice. These scores tell us how much the predicted and real areas overlap.

Data Flow - 5 Stages

1Input images and ground truth masks

100 images x 128 x 128 pixels→Load images and their true segmentation masks→100 images x 128 x 128 pixels (images), 100 masks x 128 x 128 pixels (masks)

Image of a cat and mask showing cat pixels as 1, background as 0

↓

2Preprocessing

100 images x 128 x 128 pixels→Normalize pixel values to 0-1 range→100 images x 128 x 128 pixels (normalized)

Pixel value 150 becomes 0.59

↓

3Model prediction

100 images x 128 x 128 pixels→Model predicts mask probabilities for each pixel→100 predicted masks x 128 x 128 pixels (values 0-1)

Pixel predicted as 0.8 means 80% chance of object

↓

4Thresholding

100 predicted masks x 128 x 128 pixels (0-1)→Convert probabilities to binary masks using 0.5 cutoff→100 binary predicted masks x 128 x 128 pixels (0 or 1)

Pixel 0.8 becomes 1, pixel 0.3 becomes 0

↓

5Evaluation metrics calculation

100 binary predicted masks and 100 ground truth masks x 128 x 128 pixels→Calculate IoU and Dice scores for each mask pair→100 IoU scores, 100 Dice scores (values 0-1)

IoU = 0.75, Dice = 0.85 for one image

Training Trace - Epoch by Epoch

Loss: 0.65 |****
       0.50 |******
       0.40 |********
       0.32 |**********
       0.28 |***********
Epochs -> 1    2    3    4    5

Epoch	Loss ↓	Accuracy ↑	Observation
1	0.65	0.60	Model starts learning, loss high, accuracy low
2	0.50	0.72	Loss decreases, accuracy improves
3	0.40	0.80	Model getting better at segmentation
4	0.32	0.85	Loss continues to drop, accuracy rises
5	0.28	0.88	Training converging with good accuracy

Prediction Trace - 5 Layers

Layer 1: Input image

Layer 2: Model convolution layers

Layer 3: Final sigmoid layer

Layer 4: Thresholding

Layer 5: IoU and Dice calculation

Model Quiz - 3 Questions

What does an IoU score of 1.0 mean?

A Predicted mask is empty

B No overlap between predicted and true masks

C Perfect overlap between predicted and true masks

D Ground truth mask is empty

Key Insight

IoU and Dice scores are important to measure how well a model segments objects in images. They focus on overlap quality, which accuracy alone cannot capture. This helps us understand if the model truly learns to separate objects from background.