R-CNN family overview in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does R-CNN stand for in computer vision?

R-CNN stands for Region-based Convolutional Neural Network. It is a method to detect objects by first proposing regions and then classifying them.

intermediate

How does Fast R-CNN improve over the original R-CNN?

Fast R-CNN processes the whole image with a single CNN to create a feature map, then extracts features for each region proposal, making it faster and more efficient than R-CNN.

intermediate

What is the main innovation of Faster R-CNN compared to Fast R-CNN?

Faster R-CNN introduces a Region Proposal Network (RPN) that shares convolutional features with the detection network, allowing region proposals to be generated quickly and integrated into the model.

advanced

Why is Mask R-CNN important in the R-CNN family?

Mask R-CNN extends Faster R-CNN by adding a branch that predicts a pixel-level mask for each detected object, enabling instance segmentation along with object detection.

beginner

List the main steps in the original R-CNN pipeline.

1. Generate region proposals using selective search.
2. Warp each region to a fixed size.
3. Extract features using a CNN.
4. Classify each region with SVM.
5. Refine bounding boxes with regression.

What is the main drawback of the original R-CNN method?

A It is slow because it runs CNN separately on each region proposal.

B It cannot detect multiple objects.

C It does not use convolutional neural networks.

D It does not generate region proposals.

Original R-CNN runs CNN on each region proposal independently, which is slow and inefficient.

Which R-CNN variant introduced the Region Proposal Network (RPN)?

A R-CNN

B Faster R-CNN

C Mask R-CNN

D Fast R-CNN

Faster R-CNN introduced the RPN to generate region proposals efficiently within the network.

What additional output does Mask R-CNN provide compared to Faster R-CNN?

A Bounding box coordinates

B Class labels

C Region proposals

D Pixel-level masks for objects

Mask R-CNN adds a mask branch that predicts pixel-level segmentation masks for each detected object.

How does Fast R-CNN speed up processing compared to R-CNN?

A By sharing convolutional features for all proposals in one pass

B By using a smaller CNN

C By skipping region proposals

D By using SVM classifiers

Fast R-CNN computes convolutional features once for the whole image, then extracts features for each region proposal from this shared map.

Which step is NOT part of the original R-CNN pipeline?

A Selective search for region proposals

B Feature extraction with CNN

C End-to-end training of the whole network

D Bounding box regression

Original R-CNN trains components separately and does not do end-to-end training.

Explain the evolution of the R-CNN family from R-CNN to Mask R-CNN, focusing on how each version improves speed and functionality.

Think about what bottlenecks each version addresses and what new features are added.

Describe the role of the Region Proposal Network (RPN) in Faster R-CNN and why it is important.

Consider how region proposals were generated before and how RPN changes that.

Practice

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

easy

A. To enhance image resolution

B. To generate captions for images

C. To detect edges in images

D. To find and classify objects in images by proposing regions

Solution

1. Step 1: Understand R-CNN model goal

   The R-CNN family is designed to locate objects by proposing regions and then classify them.

2. Step 2: Compare options with model purpose

   Only To find and classify objects in images by proposing regions matches the goal of finding and classifying objects using region proposals.

3. Final Answer:

   To find and classify objects in images by proposing regions -> Option D

4. Quick Check:

   R-CNN purpose = find and classify objects [OK]

Hint: R-CNN = Region proposals + Classification [OK]

Common Mistakes:

• Confusing R-CNN with image captioning models
• Thinking R-CNN enhances image quality
• Mixing edge detection with object detection

2. Which of the following is the correct sequence of steps in the original R-CNN pipeline?

easy

A. Classify entire image, extract regions, refine bounding boxes

B. Refine bounding boxes, extract regions, classify regions

C. Extract regions, classify regions, refine bounding boxes

D. Extract regions, refine bounding boxes, classify entire image

Solution

1. Step 1: Recall R-CNN pipeline steps

   R-CNN first extracts region proposals, then classifies each region, and finally refines bounding boxes.

2. Step 2: Match steps with options

   Extract regions, classify regions, refine bounding boxes correctly lists the steps in order: extract regions, classify, then refine boxes.

3. Final Answer:

   Extract regions, classify regions, refine bounding boxes -> Option C

4. Quick Check:

   R-CNN steps = extract, classify, refine [OK]

Hint: Remember: Propose regions first, then classify [OK]

Common Mistakes:

• Classifying before extracting regions
• Refining boxes before classification
• Mixing order of steps

3. Given the following code snippet for Faster R-CNN, what is the output shape of the feature map if the input image is 224x224 and the backbone reduces size by a factor of 16?

input_image = torch.randn(1, 3, 224, 224)
features = backbone(input_image)
print(features.shape)

medium

A. [1, C, 14, 14]

B. [1, C, 7, 7]

C. [1, C, 28, 28]

D. [1, C, 224, 224]

Solution

1. Step 1: Calculate spatial size after backbone

   The backbone reduces the input size by factor 16, so 224 / 16 = 14.

2. Step 2: Determine output shape format

   Output shape is batch size 1, channels C (depends on backbone), height 14, width 14.

3. Final Answer:

   [1, C, 14, 14] -> Option A

4. Quick Check:

   224/16 = 14, so output height and width = 14 [OK]

Hint: Divide input size by backbone stride for output size [OK]

Common Mistakes:

• Using 7 instead of 14 for output size
• Confusing channels with spatial dimensions
• Assuming no size reduction

4. You have a Mask R-CNN model but it is not producing masks for detected objects. Which of the following is the most likely cause?

medium

A. The backbone network is too shallow

B. The model was trained without the mask branch enabled

C. The input images are grayscale instead of RGB

D. The bounding box proposals are too large

Solution

1. Step 1: Understand Mask R-CNN mask output

   Mask R-CNN produces masks only if the mask branch is included and trained.

2. Step 2: Analyze options for mask absence

   If the mask branch is disabled during training, no masks will be produced, making The model was trained without the mask branch enabled correct.

3. Final Answer:

   The model was trained without the mask branch enabled -> Option B

4. Quick Check:

   Mask branch enabled = masks output [OK]

Hint: Masks need mask branch enabled and trained [OK]

Common Mistakes:

• Blaming backbone depth for missing masks
• Assuming grayscale input stops mask output
• Thinking bounding box size affects mask generation

5. You want to improve the speed of an R-CNN model without losing much accuracy. Which approach from the R-CNN family is best suited for this?

hard

A. Use Faster R-CNN with a Region Proposal Network (RPN)

B. Use Fast R-CNN with selective search region proposals

C. Use Mask R-CNN with added mask prediction

D. Use the original R-CNN with SVM classifiers

Solution

1. Step 1: Identify speed improvements in R-CNN family

   Faster R-CNN improves speed by integrating a Region Proposal Network to generate proposals efficiently.

2. Step 2: Compare options for speed and accuracy

   Fast R-CNN still uses slow selective search; Mask R-CNN adds mask overhead; original R-CNN is slow. So Faster R-CNN is best.

3. Final Answer:

   Use Faster R-CNN with a Region Proposal Network (RPN) -> Option A

4. Quick Check:

   Faster R-CNN = speed + accuracy via RPN [OK]

Hint: Faster R-CNN uses RPN for faster proposals [OK]

Common Mistakes:

• Choosing Fast R-CNN which still uses slow proposals
• Adding mask prediction which slows model
• Using original R-CNN which is slow