Random erasing in Computer Vision - Model Pipeline Trace

Model Pipeline - Random erasing

This pipeline shows how random erasing helps a computer vision model learn better by randomly hiding parts of images during training. This makes the model stronger and less likely to get confused by small changes.

Data Flow - 4 Stages

1Input images

1000 images x 3 channels x 32 height x 32 width→Original images loaded for training→1000 images x 3 channels x 32 height x 32 width

Image of a cat with clear details

↓

2Random erasing augmentation

1000 images x 3 channels x 32 height x 32 width→Randomly erase a small rectangle area in each image by replacing pixels with random values→1000 images x 3 channels x 32 height x 32 width

Same cat image but with a small random patch erased (covered with noise)

↓

3Feature extraction

1000 images x 3 channels x 32 height x 32 width→Convolutional layers extract important features from images→1000 images x 64 feature maps x 8 height x 8 width

Feature maps highlighting edges and textures

↓

4Classification layer

1000 images x 64 feature maps x 8 height x 8 width→Fully connected layer predicts image class→1000 images x 10 classes

Predicted probabilities for 10 classes like cat, dog, car

Training Trace - Epoch by Epoch

Epochs
1 |***************...............| Loss=1.8
3 |********************..........| Loss=1.2
5 |************************......| Loss=0.9
7 |****************************..| Loss=0.7
10|*******************************| Loss=0.5

Epoch	Loss ↓	Accuracy ↑	Observation
1	1.8	0.35	Model starts learning, loss high, accuracy low
3	1.2	0.55	Loss decreases, accuracy improves as model learns features
5	0.9	0.68	Random erasing helps model generalize, accuracy rises
7	0.7	0.75	Loss continues to drop, model becomes more confident
10	0.5	0.82	Training converges with good accuracy and low loss

Prediction Trace - 4 Layers

Layer 1: Input image

Layer 2: Random erasing (only during training, skipped here)

Layer 3: Feature extraction

Layer 4: Classification layer

Model Quiz - 3 Questions

What is the main purpose of random erasing in this pipeline?

A To increase image resolution

B To hide parts of images during training to improve model robustness

C To convert images to grayscale

D To speed up training by reducing image size

Key Insight

Random erasing helps the model learn to recognize objects even when parts are missing or hidden. This makes the model more flexible and better at handling real-world images that might have noise or occlusions.

Practice

1. What is the main purpose of random erasing in computer vision training?

easy

A. To hide random parts of images to improve model robustness

B. To increase image resolution during training

C. To convert images to grayscale

D. To add noise to the entire image

Solution

1. Step 1: Understand random erasing concept

   Random erasing hides random parts of images during training to simulate missing or blocked areas.

2. Step 2: Identify the main goal

   This helps the model learn to recognize objects even if parts are missing, improving robustness.

3. Final Answer:

   To hide random parts of images to improve model robustness -> Option A

4. Quick Check:

   Random erasing = hiding parts for robustness [OK]

Hint: Random erasing hides parts, not changes resolution or color [OK]

Common Mistakes:

• Confusing random erasing with image resizing
• Thinking it adds noise to the whole image
• Believing it converts images to grayscale

2. Which of the following is the correct way to apply random erasing using PyTorch's torchvision transforms?

easy

A. transforms.RandomErase(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

B. transforms.RandomErased(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

C. transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

D. transforms.RandomEraseArea(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3))

Solution

1. Step 1: Recall PyTorch transform name

   The correct class name is RandomErasing in torchvision.transforms.

2. Step 2: Check method parameters

   Parameters like p, scale, and ratio are valid for RandomErasing.

3. Final Answer:

   transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3)) -> Option C

4. Quick Check:

   Correct class name and parameters = transforms.RandomErasing(p=0.5, scale=(0.02, 0.33), ratio=(0.3, 3.3)) [OK]

Hint: Remember exact class name: RandomErasing (no spaces or misspellings) [OK]

Common Mistakes:

• Misspelling the class name as RandomErase or RandomErased
• Using incorrect parameter names
• Confusing with other augmentation transforms

3. Consider this PyTorch code snippet applying random erasing:

import torch
import torchvision.transforms as transforms
transform = transforms.Compose([
    transforms.RandomErasing(p=1.0, scale=(0.9, 0.9), ratio=(1, 1))
])
image = torch.ones((3, 10, 10))
output = transform(image)
print(output[:, 4:6, 4:6])

What will be the printed output?

medium

A. An error because RandomErasing expects PIL images

B. A 3x2x2 tensor of zeros

C. A 3x2x2 tensor with random values

D. A 3x2x2 tensor of ones

Solution

1. Step 1: Understand RandomErasing behavior

   With p=1.0, random erasing always applies. The erased area is set to zero by default.

2. Step 2: Analyze scale and ratio

   Scale=(0.9, 0.9) and ratio=(1, 1) fix the erased area to 90% of image size (~9x9 block) at random location near edge.

3. Step 3: Check printed slice

   The printed slice output[:, 4:6, 4:6] (center 2x2) is always covered by the large erased area, so it will be zeros.

4. Final Answer:

   A 3x2x2 tensor of zeros -> Option B

5. Quick Check:

   RandomErasing sets erased area to zero [OK]

Hint: Erased area pixels become zero tensors [OK]

Common Mistakes:

• Assuming erased area keeps original values
• Thinking erased area has random noise
• Believing RandomErasing only works on PIL images

4. You wrote this code to apply random erasing but get an error:

transform = transforms.RandomErasing(p=0.5)
image = Image.open('cat.jpg')
output = transform(image)

What is the likely cause of the error?

medium

A. RandomErasing requires grayscale images only

B. The probability p must be 1.0

C. Image file path is incorrect

D. RandomErasing expects a tensor, not a PIL image

Solution

1. Step 1: Check input type for RandomErasing

   RandomErasing in torchvision expects a tensor input, not a PIL image.

2. Step 2: Identify missing transform step

   Missing transforms.ToTensor() before RandomErasing causes type error.

3. Final Answer:

   RandomErasing expects a tensor, not a PIL image -> Option D

4. Quick Check:

   RandomErasing input = tensor, not PIL [OK]

Hint: Always convert PIL image to tensor before RandomErasing [OK]

Common Mistakes:

• Passing PIL images directly to RandomErasing
• Assuming p must be 1.0 to work
• Thinking RandomErasing only works on grayscale

5. You want to improve your image classifier's robustness by combining random erasing with another augmentation. Which combination below is best practice?

hard

A. Use random erasing after converting images to tensors and normalize them

B. Apply random erasing before resizing images to fixed size

C. Apply random erasing on raw PIL images without any other transforms

D. Use random erasing only during testing, not training

Solution

1. Step 1: Understand transform order

   Random erasing requires tensor input, so it must come after ToTensor().

2. Step 2: Combine with normalization

   Normalization after tensor conversion is standard; random erasing fits well after these steps during training.

3. Step 3: Avoid applying random erasing before resizing or during testing

   Applying before resizing can cause errors; random erasing is a training augmentation only.

4. Final Answer:

   Use random erasing after converting images to tensors and normalize them -> Option A

5. Quick Check:

   Random erasing after ToTensor and normalize = best practice [OK]

Hint: Random erasing after ToTensor and normalize during training [OK]

Common Mistakes:

• Applying random erasing on raw PIL images
• Using random erasing during testing phase
• Applying random erasing before resizing images