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.