U-Net architecture in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main purpose of the U-Net architecture in machine learning?

U-Net is mainly used for image segmentation, which means dividing an image into meaningful parts or regions, like separating objects from the background.

beginner

Describe the general shape and structure of the U-Net architecture.

U-Net has a U-shaped structure with two parts: a contracting path (encoder) that captures context by shrinking the image, and an expanding path (decoder) that recovers spatial details to produce a segmented output.

intermediate

What role do skip connections play in U-Net?

Skip connections link layers from the contracting path to the expanding path, helping the model keep important details lost during shrinking, which improves segmentation accuracy.

intermediate

How does the contracting path in U-Net process the input image?

The contracting path uses repeated convolution and pooling layers to reduce the image size while extracting important features, similar to zooming out to see the bigger picture.

beginner

What is the output of a U-Net model?

The output is a segmented image where each pixel is classified into a category, showing which part of the image belongs to which object or background.

What is the main task U-Net is designed for?

A Image generation

B Image segmentation

C Object detection

D Image classification

U-Net is specifically designed for image segmentation, which means labeling each pixel in an image.

What does the 'U' shape in U-Net represent?

A The shape of the input images

B The shape of the output mask

C The structure with contracting and expanding paths

D The shape of the loss curve

The 'U' shape refers to the network's structure with a contracting path down and an expanding path up.

Why are skip connections important in U-Net?

A They help recover spatial details lost during downsampling

B They reduce the number of parameters

C They speed up training

D They add noise to the model

Skip connections pass detailed information from the contracting path to the expanding path to improve segmentation.

Which operation is commonly used in the contracting path of U-Net?

A Dropout

B Upsampling

C Batch normalization only

D Pooling

Pooling reduces image size and helps the network learn features at different scales.

What does the output of U-Net represent?

A A segmented image with pixel-wise labels

B A compressed version of the input

C A single label for the whole image

D A generated new image

U-Net outputs a segmented image where each pixel is classified into a category.

Explain the main components and flow of data in the U-Net architecture.

Think about how the network shrinks and then grows the image representation.

Describe why skip connections are used in U-Net and how they improve the model's performance.

Consider what information might be lost during downsampling.

Practice

1. What is the main purpose of the U-Net architecture in computer vision?

easy

A. To compress images for storage

B. To classify images into categories

C. To find exact shapes and boundaries in images

D. To generate new images from noise

Solution

1. Step 1: Understand U-Net's design goal

   U-Net is designed to segment images, meaning it finds exact shapes and boundaries.

2. Step 2: Compare with other tasks

   Classification assigns labels, generation creates images, compression reduces size; these are not U-Net's main tasks.

3. Final Answer:

   To find exact shapes and boundaries in images -> Option C

4. Quick Check:

   U-Net = segmentation [OK]

Hint: U-Net = image segmentation for shapes [OK]

Common Mistakes:

• Confusing segmentation with classification
• Thinking U-Net generates images
• Assuming U-Net compresses images

2. Which of the following correctly describes the structure of U-Net?

easy

A. Two paths: one shrinks and one expands the image size

B. A single path that shrinks the image size

C. A path that only expands the image size

D. Multiple independent paths without connection

Solution

1. Step 1: Recall U-Net architecture parts

   U-Net has an encoder path that shrinks and a decoder path that expands the image size.

2. Step 2: Eliminate incorrect options

   Single shrinking path or only expanding path do not match U-Net. Independent paths without connection are incorrect.

3. Final Answer:

   Two paths: one shrinks and one expands the image size -> Option A

4. Quick Check:

   U-Net = encoder + decoder [OK]

Hint: U-Net has encoder and decoder paths [OK]

Common Mistakes:

• Thinking U-Net only shrinks images
• Believing U-Net only expands images
• Ignoring the connection between paths

3. Consider this simplified U-Net code snippet in Python using PyTorch:

import torch
import torch.nn as nn

class SimpleUNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.down = nn.Conv2d(1, 16, 3, padding=1)
        self.up = nn.ConvTranspose2d(16, 1, 2, stride=2)

    def forward(self, x):
        x1 = self.down(x)  # shrink
        x2 = self.up(x1)   # expand
        return x2

model = SimpleUNet()
input_tensor = torch.randn(1, 1, 64, 64)
output = model(input_tensor)
print(output.shape)

What will be the printed output shape?

medium

A. torch.Size([1, 1, 64, 64])

B. torch.Size([1, 1, 128, 128])

C. torch.Size([1, 16, 64, 64])

D. torch.Size([1, 16, 32, 32])

Solution

1. Step 1: Analyze down convolution output size

   Input is 64x64, Conv2d with kernel=3, padding=1 keeps size 64x64, output channels=16.

2. Step 2: Analyze up convolution output size

   ConvTranspose2d with kernel=2, stride=2 doubles spatial size to 128x128, output channels=1.

3. Step 3: Check actual output shape

   Output shape is (batch=1, channels=1, height=128, width=128).

4. Final Answer:

   torch.Size([1, 1, 128, 128]) -> Option B

5. Quick Check:

   Upsample doubles size = 128x128 [OK]

Hint: ConvTranspose2d with stride 2 doubles size [OK]

Common Mistakes:

• Assuming Conv2d changes size without padding
• Ignoring stride effect in ConvTranspose2d
• Mixing channel numbers in output

4. In a U-Net implementation, a student forgot to add skip connections between encoder and decoder layers. What is the most likely effect?

medium

A. The model will not train at all and cause an error

B. The model will have better accuracy due to fewer connections

C. The model will run faster and produce the same results

D. The model will lose fine details and perform worse on segmentation

Solution

1. Step 1: Understand skip connections role

   Skip connections pass fine details from encoder to decoder to improve segmentation accuracy.

2. Step 2: Effect of missing skip connections

   Without them, decoder lacks detail info, causing worse segmentation results.

3. Final Answer:

   The model will lose fine details and perform worse on segmentation -> Option D

4. Quick Check:

   Skip connections = better detail [OK]

Hint: No skip connections = loss of detail [OK]

Common Mistakes:

• Thinking fewer connections always improve accuracy
• Assuming model will error without skip connections
• Believing speed improves without accuracy loss

5. You want to improve a U-Net model's segmentation on small objects in medical images. Which change is most effective?

hard

A. Increase the depth of the encoder to capture more features

B. Remove skip connections to simplify the model

C. Use larger convolution kernels to cover bigger areas

D. Add more pooling layers to reduce spatial size aggressively

Solution

1. Step 1: Identify challenge with small objects

   Small objects need detailed features and context captured by deeper layers.

2. Step 2: Evaluate options

   Increasing encoder depth helps learn more features. Removing skip connections loses detail. Larger kernels may blur small details. More pooling reduces spatial resolution, losing small object info.

3. Final Answer:

   Increase the depth of the encoder to capture more features -> Option A

4. Quick Check:

   Deeper encoder = better small object features [OK]

Hint: Deeper encoder = better small object detection [OK]

Common Mistakes:

• Removing skip connections harms detail
• Larger kernels blur small features
• More pooling loses small object info