MixUp strategy in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create mixed inputs using MixUp.

Computer Vision

mixed_x = lambda x1, x2, lam: lam * x1 + [1] * x2

Drag options to blanks, or click blank then click option'

Alam + 1

Blam - 1

C1 - lam

Dlam

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam for the second input weight.

Adding lambda values instead of subtracting.

Using incorrect arithmetic operators.

MixUp combines two inputs weighted by lambda and (1 - lambda).

2fill in blank

medium

Complete the code to mix labels in MixUp.

Computer Vision

mixed_y = lam * y1 + [1] * y2

Drag options to blanks, or click blank then click option'

A1 - lam

Blam + 1

Clam

Dlam * 2

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam for both labels.

Multiplying lam by 2 incorrectly.

Adding lam and 1 instead of subtracting.

Labels are mixed with the same weights as inputs: lam and 1 - lam.

3fill in blank

hard

Fix the error in the MixUp lambda sampling code.

Computer Vision

lam = np.random.beta([1], [1])

Drag options to blanks, or click blank then click option'

A1.0

B0.5

C0

D2.0

Attempts:

3 left

💡 Hint

Common Mistakes

Using 1.0 which results in uniform distribution.

Using 0 which is invalid for Beta distribution.

Using 2.0 which biases mixing too much.

The MixUp lambda is sampled from a Beta distribution with alpha=beta=0.5 for stronger mixing.

4fill in blank

hard

Fill both blanks to create a MixUp batch of inputs and labels.

Computer Vision

mixed_x = lam * x + [1] * x[[2]]

Drag options to blanks, or click blank then click option'

A1 - lam

Blam

Cperm

Dx

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam for the second weight.

Using x instead of permuted indices for the second input.

MixUp uses (1 - lam) for the second input weight and permuted indices to shuffle the batch.

5fill in blank

hard

Fill all three blanks to complete the MixUp label mixing code.

Computer Vision

mixed_y = lam * y + [1] * y[[2]]  # y shape: [3]

Drag options to blanks, or click blank then click option'

A1 - lam

Bperm

C(batch_size, num_classes)

D(num_classes, batch_size)

Attempts:

3 left

💡 Hint

Common Mistakes

Using lam instead of 1 - lam.

Using wrong shape for labels.

Not using permuted indices for label mixing.

Labels are mixed with 1 - lam and permuted indices; labels usually have shape (batch_size, num_classes).

Practice

1. What is the main purpose of the MixUp strategy in computer vision?

easy

A. To blend images and labels to create smoother decision boundaries

B. To increase the size of the neural network

C. To reduce the image resolution for faster training

D. To remove noisy images from the dataset

Solution

1. Step 1: Understand MixUp's function

   MixUp combines two images and their labels to create new training samples.

2. Step 2: Identify the goal of blending

   This blending helps the model learn smoother decision boundaries and generalize better.

3. Final Answer:

   To blend images and labels to create smoother decision boundaries -> Option A

4. Quick Check:

   MixUp = blending images and labels [OK]

Hint: MixUp mixes images and labels to smooth learning [OK]

Common Mistakes:

• Thinking MixUp increases model size
• Confusing MixUp with image resizing
• Believing MixUp removes data

2. Which of the following is the correct way to generate a mixed image x_mix using MixUp with images x1, x2 and mixing coefficient lambda?

easy

A. x_mix = (1 - lambda) * x1 + lambda * x2

B. x_mix = x1 + x2

C. x_mix = lambda * (x1 + x2)

D. x_mix = lambda * x1 + (1 - lambda) * x2

Solution

1. Step 1: Recall MixUp formula for images

   MixUp creates a weighted sum: mixed image = (1 - lambda) * first image + lambda * second image.

2. Step 2: Match formula to options

   x_mix = (1 - lambda) * x1 + lambda * x2 matches this formula exactly.

3. Final Answer:

   x_mix = (1 - lambda) * x1 + lambda * x2 -> Option A

4. Quick Check:

   MixUp image = weighted sum with lambda [OK]

Hint: MixUp image = (1-lambda) * first + lambda * second [OK]

Common Mistakes:

• Swapping lambda and (1 - lambda) incorrectly
• Adding images without weights
• Multiplying sum by lambda instead of weighting separately

3. Given the following code snippet using MixUp, what will be the shape of mixed_labels?

import torch
labels1 = torch.tensor([[1, 0, 0], [0, 1, 0]])
labels2 = torch.tensor([[0, 0, 1], [1, 0, 0]])
lambda_ = 0.7
mixed_labels = lambda_ * labels1 + (1 - lambda_) * labels2
print(mixed_labels.shape)

medium

A. torch.Size([2])

B. torch.Size([3, 2])

C. torch.Size([2, 3])

D. torch.Size([3])

Solution

1. Step 1: Check input label shapes

   labels1 and labels2 are tensors with shape [2, 3] (2 samples, 3 classes).

2. Step 2: Mixing labels keeps shape

   MixUp combines labels element-wise, so mixed_labels shape remains [2, 3].

3. Final Answer:

   torch.Size([2, 3]) -> Option C

4. Quick Check:

   Mixed labels shape = input labels shape [OK]

Hint: MixUp label shape matches original labels [OK]

Common Mistakes:

• Confusing batch and class dimensions
• Assuming shape changes after mixing
• Misreading tensor dimensions

4. Identify the error in this MixUp implementation snippet:

def mixup_data(x1, x2, y1, y2, alpha=1.0):
    lam = np.random.beta(alpha, alpha)
    x_mix = lam * x1 + (1 - lam) * x2
    y_mix = lam * y1 + lam * y2
    return x_mix, y_mix

medium

A. The beta distribution parameters are incorrect

B. The function should return only mixed images

C. The images should not be mixed with weights

D. The label mixing formula should use (1 - lam) for y2, not lam

Solution

1. Step 1: Review label mixing formula

   Labels must be mixed as y_mix = lam * y1 + (1 - lam) * y2 to match image mixing.

2. Step 2: Identify mismatch in code

   The code incorrectly uses lam * y2 instead of (1 - lam) * y2.

3. Final Answer:

   The label mixing formula should use (1 - lam) for y2, not lam -> Option D

4. Quick Check:

   Label weights must sum to 1 [OK]

Hint: Label weights must add to 1 in MixUp [OK]

Common Mistakes:

• Using same weight for both labels
• Ignoring beta distribution for lambda
• Returning incomplete outputs

5. You want to apply MixUp to a dataset with 10,000 images and 5 classes. If you set the MixUp parameter alpha very high (e.g., 100), what is the likely effect on training?

hard

A. The model will train faster due to clearer labels

B. The mixed images will be almost equal blends, possibly making labels ambiguous

C. The mixed images will be mostly original images with little blending

D. The model will ignore MixUp and train normally

Solution

1. Step 1: Understand beta distribution with high alpha

   High alpha in beta distribution centers lambda near 0.5, causing equal blending.

2. Step 2: Consider impact on labels and images

   Equal blending creates ambiguous images and soft labels, which may confuse the model.

3. Final Answer:

   The mixed images will be almost equal blends, possibly making labels ambiguous -> Option B

4. Quick Check:

   High alpha = balanced blends, ambiguous labels [OK]

Hint: High alpha means balanced mixes, can confuse model [OK]

Common Mistakes:

• Thinking high alpha means less mixing
• Assuming faster training with high alpha
• Believing MixUp is ignored with extreme alpha