MixUp strategy in Computer Vision - Model Pipeline Trace

Model Pipeline - MixUp strategy

The MixUp strategy blends pairs of images and their labels to create new training samples. This helps the model learn smoother decision boundaries and improves generalization.

Data Flow - 4 Stages

1Original Dataset

1000 images x 32x32 pixels x 3 channels→Raw images with one-hot encoded labels→1000 images x 32x32 pixels x 3 channels

Image1: cat, Label1: [1,0,0]; Image2: dog, Label2: [0,1,0]

↓

2MixUp Pairing

1000 images x 32x32 pixels x 3 channels→Randomly pair images and labels for mixing→500 pairs of images and labels

Pair: (Image1, Image2), Labels: ([1,0,0], [0,1,0])

↓

3MixUp Blending

500 pairs of images and labels→Blend images and labels using lambda from Beta distribution→500 mixed images x 32x32 pixels x 3 channels

Mixed Image = 0.7*Image1 + 0.3*Image2; Mixed Label = 0.7*[1,0,0] + 0.3*[0,1,0]

↓

4Model Training

500 mixed images x 32x32 pixels x 3 channels→Train model on mixed images and soft labels→Model updated weights

Model learns from blended images and labels

Training Trace - Epoch by Epoch

Loss
1.2 |****
0.9 |***
0.7 |**
0.55|*
0.45| 
    +------------
     1  2  3  4  5
     Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.2	0.45	Initial loss high, accuracy low as model starts learning
2	0.9	0.60	Loss decreases, accuracy improves with MixUp regularization
3	0.7	0.72	Model learns smoother boundaries, better generalization
4	0.55	0.80	Continued improvement, loss steadily decreases
5	0.45	0.85	Training converges with higher accuracy and lower loss

Prediction Trace - 4 Layers

Layer 1: Input Mixed Image

Layer 2: Convolutional Layers

Layer 3: Fully Connected Layers

Layer 4: Softmax Activation

Model Quiz - 3 Questions

What is the main purpose of mixing two images and their labels in MixUp?

A To remove noisy data from the dataset

B To increase the size of the test set

C To create new training examples that help the model generalize better

D To speed up the training process

Key Insight

MixUp helps the model learn from blended images and labels, encouraging smoother decision boundaries and better generalization by training on a richer set of examples.