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.<br>2. Warp each region to a fixed size.<br>3. Extract features using a CNN.<br>4. Classify each region with SVM.<br>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.