Mask R-CNN overview in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the primary purpose of Mask R-CNN?

Mask R-CNN is a popular model in computer vision. What is its main task?

A Classify images into categories like cats or dogs

B Detect objects and draw bounding boxes around them

C Detect objects, classify them, and generate pixel-level masks

D Generate captions describing the content of images

💡 Hint

Think about what extra output Mask R-CNN produces beyond bounding boxes.

Mask R-CNN extends object detection by adding a mask prediction branch that outputs a pixel-level mask for each detected object.

❓ Model Choice

intermediate

Which component is unique to Mask R-CNN compared to Faster R-CNN?

Mask R-CNN builds on Faster R-CNN. Which part is added uniquely in Mask R-CNN?

A Region Proposal Network (RPN)

B A branch for predicting segmentation masks

C Non-maximum suppression for filtering boxes

D Fully connected layers for classification

💡 Hint

Consider what extra output Mask R-CNN produces that Faster R-CNN does not.

Mask R-CNN adds a mask prediction branch that outputs a binary mask for each detected object, which Faster R-CNN lacks.

❓ Predict Output

advanced

What is the shape of the mask output for one detected object?

Assume Mask R-CNN outputs a mask tensor for one detected object. If the mask size is 28x28 pixels, what is the shape of this mask output?

Computer Vision

mask_output = model.predict_mask(single_object_region)
print(mask_output.shape)

A (1, 28, 28)

B (28, 28, 1)

C (28, 28)

D (1, 1, 28, 28)

💡 Hint

Mask R-CNN outputs masks with a batch or channel dimension.

The mask output shape includes a channel dimension for the single mask, so it is (1, 28, 28).

❓ Metrics

advanced

Which metric best evaluates Mask R-CNN's mask quality?

When assessing Mask R-CNN's performance, which metric specifically measures how well the predicted masks match the true object shapes?

A Confusion matrix

B Mean Average Precision (mAP) for bounding boxes

C Classification accuracy

D Intersection over Union (IoU) for masks

💡 Hint

Think about a metric that compares overlap between predicted and true masks.

IoU measures the overlap between predicted and ground truth masks, making it ideal for evaluating mask quality.

🔧 Debug

expert

Why might Mask R-CNN produce poor mask predictions despite good bounding boxes?

After training Mask R-CNN, you notice bounding boxes are accurate but masks are poor. Which issue is the most likely cause?

A The mask branch uses a too low resolution feature map

B The Region Proposal Network failed to generate proposals

C The classification loss is too high

D Non-maximum suppression threshold is too low

💡 Hint

Consider what affects mask detail quality in the network.

If the mask branch uses low resolution features, it cannot capture fine details, leading to poor masks despite good boxes.

Practice

1. What is the main purpose of Mask R-CNN in computer vision?

easy

A. To generate captions for images

B. To classify images into categories

C. To enhance image resolution

D. To detect objects and find their exact shapes in images

Solution

1. Step 1: Understand Mask R-CNN's function

   Mask R-CNN is designed to detect objects and also predict masks that show the exact shape of each object.

2. Step 2: Compare with other tasks

   Unlike classification or captioning, Mask R-CNN focuses on locating and segmenting objects precisely.

3. Final Answer:

   To detect objects and find their exact shapes in images -> Option D

4. Quick Check:

   Mask R-CNN = Object detection + precise shape masks [OK]

Hint: Mask R-CNN = detection + mask prediction [OK]

Common Mistakes:

• Confusing Mask R-CNN with image classification models
• Thinking it only detects bounding boxes without masks
• Assuming it generates image captions

2. Which component is NOT part of the Mask R-CNN architecture?

easy

A. Region Proposal Network (RPN)

B. Mask branch for pixel-level segmentation

C. Recurrent Neural Network (RNN) for sequence modeling

D. Fully Connected Layer for classification

Solution

1. Step 1: Identify Mask R-CNN components

   Mask R-CNN includes RPN for proposing regions, fully connected layers for classifying objects, and a mask branch for segmentation.

2. Step 2: Check for unrelated components

   RNNs are used for sequence data like text or speech, not for Mask R-CNN's image segmentation tasks.

3. Final Answer:

   Recurrent Neural Network (RNN) for sequence modeling -> Option C

4. Quick Check:

   Mask R-CNN excludes RNNs [OK]

Hint: Mask R-CNN uses CNNs, not RNNs [OK]

Common Mistakes:

• Thinking RNNs are part of Mask R-CNN
• Confusing mask branch with classification layers
• Ignoring the role of RPN

3. Given the following simplified Mask R-CNN output for an image, what does the mask represent?
masks = [[[0,1,1],[0,1,1],[0,0,0]], [[1,0,0],[1,1,0],[0,0,0]]]
Each inner list is a 3x3 mask for one object. What does a '1' indicate?

medium

A. Pixels belonging to the object

B. Background pixels

C. Pixels with low confidence

D. Pixels to be ignored

Solution

1. Step 1: Understand mask values in Mask R-CNN

   Mask R-CNN outputs masks where '1' marks pixels that belong to the detected object, and '0' marks background.

2. Step 2: Interpret the given mask arrays

   In the given masks, '1's show the shape of each object in the 3x3 grid.

3. Final Answer:

   Pixels belonging to the object -> Option A

4. Quick Check:

   Mask '1' = object pixel [OK]

Hint: '1' in mask means object pixel [OK]

Common Mistakes:

• Confusing '1' with background
• Assuming '1' means low confidence
• Thinking '1' means ignored pixels

4. You run Mask R-CNN but get an error: 'ValueError: mask size mismatch'. What is the most likely cause?

medium

A. The mask output size does not match the region proposal size

B. The input image is grayscale instead of color

C. The model is missing the classification head

D. The learning rate is too high

Solution

1. Step 1: Understand mask size mismatch error

   This error usually means the predicted mask dimensions don't match the size of the proposed region where the mask should be applied.

2. Step 2: Check other options

   Input image color or missing classification head won't cause mask size mismatch. Learning rate affects training, not mask size.

3. Final Answer:

   The mask output size does not match the region proposal size -> Option A

4. Quick Check:

   Mask size must match proposal size [OK]

Hint: Check mask and proposal sizes match [OK]

Common Mistakes:

• Blaming input image color for mask size error
• Ignoring mask and proposal size relation
• Confusing training hyperparameters with output shape errors

5. You want to improve Mask R-CNN's mask accuracy on small objects in images. Which approach is best?

hard

A. Remove the mask branch and only use bounding boxes

B. Increase the resolution of the feature maps used for mask prediction

C. Use a simpler backbone network to speed up training

D. Reduce the number of region proposals generated by RPN

Solution

1. Step 1: Identify how to improve mask accuracy for small objects

   Small objects need finer details, so increasing feature map resolution helps the mask branch capture small shapes better.

2. Step 2: Evaluate other options

   Reducing proposals may miss objects, simpler backbone reduces feature quality, and removing mask branch loses mask prediction entirely.

3. Final Answer:

   Increase the resolution of the feature maps used for mask prediction -> Option B

4. Quick Check:

   Higher resolution features = better small object masks [OK]

Hint: Higher feature resolution helps small object masks [OK]

Common Mistakes:

• Reducing proposals thinking it improves accuracy
• Using simpler backbone hurting feature quality
• Removing mask branch losing mask output