Augmentation policy search (AutoAugment) in Computer Vision - Model Pipeline Trace

Model Pipeline - Augmentation policy search (AutoAugment)

This pipeline automatically finds the best ways to change images to help a model learn better. It tries different image changes, like flipping or color shifts, to improve the model's ability to recognize objects.

Data Flow - 5 Stages

1Raw Image Dataset

50000 images x 32 x 32 x 3→Original CIFAR-10 images→50000 images x 32 x 32 x 3

Image of a cat with RGB colors

↓

2Augmentation Policy Search

50000 images x 32 x 32 x 3→Apply different image transformations like rotate, shear, color adjust with varying strengths to find best policies→50000 images x 32 x 32 x 3 (augmented)

Image rotated 15 degrees and brightness increased by 20%

↓

3Train/Test Split

50000 images x 32 x 32 x 3→Split dataset into training (45000) and validation (5000)→45000 images x 32 x 32 x 3 (train), 5000 images x 32 x 32 x 3 (validation)

Training image of a dog, validation image of a truck

↓

4Model Training

45000 images x 32 x 32 x 3→Train convolutional neural network on augmented images→Trained model weights

CNN learns to recognize objects better with augmented images

↓

5Validation Evaluation

5000 images x 32 x 32 x 3→Evaluate model accuracy on validation set→Accuracy score (percentage)

Model achieves 88% accuracy on validation images

Training Trace - Epoch by Epoch

Loss
1.2 |****
1.0 |***
0.8 |**
0.6 |**
0.4 |*
0.2 |
    +----------------
     1 5 10 15 20 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.20	0.55	Model starts learning with moderate accuracy
5	0.75	0.75	Loss decreases and accuracy improves as model learns
10	0.50	0.85	Model shows strong learning with good accuracy
15	0.40	0.89	Loss continues to decrease, accuracy nearing 90%
20	0.35	0.91	Model converges with high accuracy and low loss

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: Augmentation Policy Applied

Layer 3: Convolutional Layer

Layer 4: Pooling Layer

Layer 5: Fully Connected Layer

Layer 6: Softmax Activation

Model Quiz - 3 Questions

What is the main purpose of the augmentation policy search step?

A To split the dataset into training and validation sets

B To find the best image changes that help the model learn better

C To evaluate the model accuracy on test data

D To reduce the size of images for faster training

Key Insight

AutoAugment helps the model learn better by automatically finding the best image changes. This makes the model more accurate and robust by showing it many useful variations of the images during training.