Data augmentation importance in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Data augmentation importance

Which metric matters for Data Augmentation and WHY

Data augmentation helps models see more varied examples by changing images slightly. This usually improves accuracy and generalization. We focus on validation accuracy and validation loss to check if the model learns well on new, unseen images. Higher accuracy and lower loss on validation data mean augmentation is helping the model avoid overfitting and perform better in real life.

Confusion Matrix Example

Imagine a model classifying images into cats and dogs. After training with augmentation, the confusion matrix might look like this:

      | Predicted Cat | Predicted Dog |
      |--------------|---------------|
      | True Cat: 45 | False Dog: 5  |
      | False Cat: 3 | True Dog: 47  |
    

Total samples = 45 + 5 + 3 + 47 = 100

From this, we calculate:

• Precision (Cat) = 45 / (45 + 3) = 0.94
• Recall (Cat) = 45 / (45 + 5) = 0.90
• Accuracy = (45 + 47) / 100 = 0.92

This shows the model is good at recognizing cats and dogs after augmentation.

Precision vs Recall Tradeoff with Data Augmentation

Data augmentation can help balance precision and recall by making the model robust to variations.

• High Precision, Low Recall: Model is very sure when it predicts a class but misses many true cases. For example, it only labels very clear cat images as cats, missing some cats that look different.
• High Recall, Low Precision: Model finds most cats but sometimes mistakes dogs for cats.

Augmentation helps increase both by showing the model many versions of cats and dogs, so it learns to recognize them better in different conditions.

Good vs Bad Metric Values for Data Augmentation

Good:

• Validation accuracy improves or stays stable compared to no augmentation.
• Validation loss decreases, showing better learning on new data.
• Balanced precision and recall above 85% for key classes.

Bad:

• Validation accuracy drops significantly, meaning augmentation is hurting learning.
• Validation loss increases or fluctuates wildly.
• Precision or recall very low, showing model confusion.

Common Pitfalls in Metrics with Data Augmentation

• Overfitting despite augmentation: Augmentation is not a fix-all; if the model is too complex, it can still memorize training data.
• Data leakage: Augmented images too similar to validation images can give false high accuracy.
• Ignoring class imbalance: Augmentation might increase some classes more than others, skewing metrics.
• Accuracy paradox: High accuracy can hide poor performance on rare classes; always check precision and recall.

Self Check

Your model trained with data augmentation shows 98% accuracy but only 12% recall on a rare class like fraud detection. Is it good?

Answer: No, it is not good. The low recall means the model misses most fraud cases, which is critical. High accuracy is misleading because most data is non-fraud. You need to improve recall, possibly by better augmentation or other techniques.

Key Result

Data augmentation improves validation accuracy and recall by exposing the model to varied data, helping it generalize better.

Practice

1. Why is data augmentation important in training computer vision models?

easy

A. It increases the variety of training images to help the model generalize better.

B. It reduces the size of the training dataset to speed up training.

C. It removes noisy images from the dataset automatically.

D. It guarantees 100% accuracy on the training data.

Solution

1. Step 1: Understand data augmentation purpose

   Data augmentation creates new images by slightly changing existing ones to increase variety.

2. Step 2: Connect augmentation to model learning

   More variety helps the model learn features that work on new, unseen images, improving generalization.

3. Final Answer:

   It increases the variety of training images to help the model generalize better. -> Option A

4. Quick Check:

   Data augmentation = better generalization [OK]

Hint: Think: more image variety means better learning [OK]

Common Mistakes:

• Confusing augmentation with data reduction
• Believing augmentation removes bad images
• Assuming augmentation guarantees perfect accuracy

2. Which of the following is a correct way to apply horizontal flip augmentation using Python's torchvision library?

easy

A. transforms.FlipHorizontal(prob=0.5)

B. transforms.HorizontalFlip(0.5)

C. transforms.RandomHorizontalFlip(p=0.5)

D. transforms.RandomFlipHorizontal()

Solution

1. Step 1: Recall torchvision syntax for horizontal flip

   The correct transform is RandomHorizontalFlip with a probability parameter p.

2. Step 2: Check each option's correctness

   Only transforms.RandomHorizontalFlip(p=0.5) matches the correct syntax and parameter name.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=0.5) -> Option C

4. Quick Check:

   Correct torchvision flip syntax = transforms.RandomHorizontalFlip(p=0.5) [OK]

Hint: Look for 'RandomHorizontalFlip' with parameter p= [OK]

Common Mistakes:

• Using wrong class names like HorizontalFlip
• Incorrect parameter names like prob instead of p
• Missing the probability parameter

3. What will be the output shape of the augmented image after applying the following PyTorch transform?

transform = transforms.Compose([
  transforms.Resize((128, 128)),
  transforms.RandomRotation(30),
  transforms.ToTensor()
])
augmented_image = transform(original_image)

medium

A. [128, 3, 128]

B. [128, 128, 3]

C. [1, 128, 128]

D. [3, 128, 128]

Solution

1. Step 1: Analyze the transform steps

   Resize changes image to 128x128 pixels. RandomRotation keeps size same. ToTensor converts image to tensor with channels first.

2. Step 2: Determine tensor shape format

   PyTorch tensors from images have shape [channels, height, width]. For RGB images, channels=3.

3. Final Answer:

   [3, 128, 128] -> Option D

4. Quick Check:

   PyTorch image tensor shape = [channels, height, width] [OK]

Hint: PyTorch image tensors are channels first: [3, H, W] [OK]

Common Mistakes:

• Confusing channel order with height and width
• Assuming rotation changes image size
• Mixing up tensor shape formats

4. You wrote this augmentation code but get an error:

transform = transforms.Compose([
  transforms.RandomRotation(45),
  transforms.RandomHorizontalFlip(0.3),
  transforms.ToTensor()
])

What is the likely cause?

medium

A. RandomHorizontalFlip expects a keyword argument p, not a positional float.

B. RandomRotation requires integer degrees, not float.

C. ToTensor must come before RandomRotation.

D. Compose cannot combine these transforms.

Solution

1. Step 1: Check RandomHorizontalFlip usage

   RandomHorizontalFlip requires the probability parameter as a keyword argument p=, not a positional argument.

2. Step 2: Verify other transform usages

   RandomRotation accepts float degrees, ToTensor can be last, Compose supports these transforms.

3. Final Answer:

   RandomHorizontalFlip expects a keyword argument p, not a positional float. -> Option A

4. Quick Check:

   RandomHorizontalFlip(p=0.3) correct syntax [OK]

Hint: Check if transform params use correct keywords [OK]

Common Mistakes:

• Passing probability as positional argument
• Thinking rotation degrees must be integer
• Misordering transforms in Compose

5. You have a small dataset of 100 images for a classification task. Which data augmentation strategy will most likely improve your model's ability to recognize objects in new photos?

hard

A. Only resize images to a fixed size without any other changes.

B. Apply random flips, rotations up to 30 degrees, and brightness changes during training.

C. Add Gaussian noise to all images without any geometric transforms.

D. Train without augmentation but increase model layers.

Solution

1. Step 1: Consider dataset size and augmentation needs

   Small datasets benefit from augmentations that create varied views of images to prevent overfitting.

2. Step 2: Evaluate augmentation types

   Random flips, rotations, and brightness changes simulate real-world variations, improving generalization better than noise alone or no augmentation.

3. Final Answer:

   Apply random flips, rotations up to 30 degrees, and brightness changes during training. -> Option B

4. Quick Check:

   Varied augmentations = better generalization on small data [OK]

Hint: Use varied simple transforms for small datasets [OK]

Common Mistakes:

• Ignoring augmentation on small datasets
• Using only noise without geometric changes
• Relying on bigger models instead of data variety