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.