Image segmentation basics in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is image segmentation in simple terms?

Image segmentation is like coloring a picture by dividing it into parts. It means splitting an image into pieces where each piece shows something important, like a person or a tree.

beginner

What is the difference between classification and segmentation?

Classification says what is in the whole image (like 'cat' or 'dog'). Segmentation tells exactly where each object is by coloring each pixel with a label.

intermediate

What is a common neural network architecture used for image segmentation?

U-Net is a popular network for image segmentation. It looks like a U shape and helps the model learn both the big picture and small details.

beginner

What does a segmentation mask represent?

A segmentation mask is an image where each pixel has a label showing which object or background it belongs to. It’s like a coloring book page for the model.

intermediate

Why do we use metrics like IoU (Intersection over Union) in segmentation?

IoU measures how well the predicted segmentation matches the true segmentation by comparing overlapping areas. It helps us know if the model is doing a good job.

What does image segmentation do?

A Divides an image into meaningful parts

B Classifies the whole image into one category

C Generates captions for images

D Resizes images to smaller dimensions

Image segmentation splits an image into parts that represent different objects or regions.

Which architecture is commonly used for image segmentation?

A ResNet

B RNN

C Transformer

D U-Net

U-Net is designed specifically for image segmentation tasks.

What is a segmentation mask?

A A text description of the image

B A blurred version of the original image

C An image with pixel-wise labels

D A resized image

A segmentation mask labels each pixel to show which object it belongs to.

What does IoU measure in segmentation?

A Image brightness

B Overlap between predicted and true masks

C Model training speed

D Number of layers in the model

IoU compares how much the predicted and true segmentation masks overlap.

How is segmentation different from classification?

A Segmentation labels each pixel; classification labels the whole image

B Segmentation is faster than classification

C Classification uses images; segmentation uses text

D They are the same

Segmentation assigns labels to every pixel, while classification assigns one label to the entire image.

Explain what image segmentation is and why it is useful.

Think about how you would color different objects in a photo.

Describe the U-Net architecture and its role in image segmentation.

Imagine a network that zooms out and then zooms back in.

Practice

1. What is the main goal of image segmentation in TensorFlow?

easy

A. To compress images without losing quality

B. To label each pixel in an image with a class

C. To generate random noise images

D. To classify the entire image into one category

Solution

1. Step 1: Understand image segmentation purpose

   Image segmentation assigns a class label to every pixel, dividing the image into meaningful parts.

2. Step 2: Compare with other tasks

   Unlike classification, which labels the whole image, segmentation works at pixel level.

3. Final Answer:

   To label each pixel in an image with a class -> Option B

4. Quick Check:

   Image segmentation = pixel-wise labeling [OK]

Hint: Segmentation means labeling pixels, not whole images [OK]

Common Mistakes:

• Confusing segmentation with image classification
• Thinking segmentation compresses images
• Believing segmentation creates random images

2. Which TensorFlow layer is commonly used to extract features for image segmentation?

easy

A. Convolutional layer

B. Dense layer

C. Dropout layer

D. Flatten layer

Solution

1. Step 1: Identify feature extraction layers

   Convolutional layers scan images to find patterns and features useful for segmentation.

2. Step 2: Understand other layers' roles

   Dense layers are for classification, dropout prevents overfitting, flatten reshapes data but doesn't extract features.

3. Final Answer:

   Convolutional layer -> Option A

4. Quick Check:

   Feature extraction = convolutional layers [OK]

Hint: Convolutional layers find image features [OK]

Common Mistakes:

• Choosing dense layers for feature extraction
• Confusing flatten with convolution
• Ignoring convolution's role in images

3. What will be the shape of the output tensor after applying a softmax activation on a segmentation model predicting 3 classes for a 128x128 image?

medium

A. (128, 128, 3)

B. (3, 128, 128)

C. (128, 3, 128)

D. (128, 128)

Solution

1. Step 1: Understand output shape for segmentation

   Each pixel has a probability for each class, so output shape is height x width x classes.

2. Step 2: Apply to given image and classes

   Image size is 128x128, classes are 3, so output shape is (128, 128, 3).

3. Final Answer:

   (128, 128, 3) -> Option A

4. Quick Check:

   Output shape = (height, width, classes) [OK]

Hint: Output shape = image size + number of classes [OK]

Common Mistakes:

• Mixing class dimension position
• Forgetting classes dimension
• Using 2D shape instead of 3D

4. Given this TensorFlow code snippet for segmentation, what is the error?

model = tf.keras.Sequential([
  tf.keras.layers.Conv2D(16, 3, activation='relu', input_shape=(64, 64, 3)),
  tf.keras.layers.Dense(3, activation='softmax')
])

medium

A. Conv2D kernel size must be 1

B. Input shape is incorrect for images

C. Activation 'relu' is invalid

D. Dense layer cannot follow Conv2D without flattening

Solution

1. Step 1: Check layer sequence

   Conv2D outputs 4D tensor, Dense expects 2D input, so flattening is needed before Dense.

2. Step 2: Validate other options

   Input shape is valid for images, 'relu' is a valid activation, kernel size 3 is allowed.

3. Final Answer:

   Dense layer cannot follow Conv2D without flattening -> Option D

4. Quick Check:

   Dense after Conv2D needs flattening [OK]

Hint: Dense layers need flat input, add Flatten after Conv2D [OK]

Common Mistakes:

• Ignoring tensor shape mismatch
• Thinking kernel size must be 1
• Misunderstanding activation functions

5. You want to train a simple segmentation model in TensorFlow. Which data do you need to provide during training?

hard

A. Only images without labels

B. Images and image-level class labels

C. Images and their pixel-level masks

D. Random noise images

Solution

1. Step 1: Identify training data for segmentation

   Segmentation requires images and masks labeling each pixel's class to learn pixel-wise predictions.

2. Step 2: Compare with other data types

   Image-level labels are for classification, no labels means no supervision, noise images are irrelevant.

3. Final Answer:

   Images and their pixel-level masks -> Option C

4. Quick Check:

   Training segmentation = images + pixel masks [OK]

Hint: Segmentation training needs pixel masks, not just labels [OK]

Common Mistakes:

• Using only image-level labels
• Training without masks
• Confusing segmentation with classification data