SSD concept in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What does SSD stand for in object detection?

SSD stands for Single Shot MultiBox Detector, a method to detect objects in images in one pass.

intermediate

How does SSD detect objects differently from two-stage detectors like Faster R-CNN?

SSD detects objects in a single step without a separate region proposal stage, making it faster but still accurate.

intermediate

What role do default boxes (anchor boxes) play in SSD?

Default boxes are pre-set boxes of different sizes and aspect ratios used to predict object locations and classes at multiple scales.

intermediate

Why does SSD use multiple feature maps at different scales?

Using multiple feature maps helps SSD detect objects of various sizes by looking at different levels of detail.

beginner

What are the main outputs of the SSD model for each default box?

For each default box, SSD outputs a class score (what object it might be) and box offsets (how to adjust the box to fit the object).

What is the main advantage of SSD over two-stage detectors?

A It detects objects in a single pass, making it faster.

B It uses more complex region proposals.

C It requires multiple passes over the image.

D It only detects one object per image.

SSD detects objects in one step without separate region proposals, which speeds up detection.

What are default boxes in SSD used for?

A To generate multiple guesses for object locations and sizes.

B To increase image resolution.

C To reduce the number of classes.

D To crop the image into smaller parts.

Default boxes are pre-defined boxes that help SSD predict where objects are and their sizes.

Why does SSD use multiple feature maps at different scales?

A To avoid using default boxes.

B To reduce the number of parameters.

C To increase training time.

D To detect objects of different sizes effectively.

Multiple feature maps let SSD detect small and large objects by looking at different detail levels.

What does SSD output for each default box?

A Only the bounding box coordinates.

B Only the class label.

C Class scores and box location adjustments.

D Image segmentation masks.

SSD predicts both what object is inside and how to adjust the box to fit it better.

Which of these is NOT a characteristic of SSD?

A Single pass detection.

B Uses region proposal network.

C Multi-scale feature maps.

D Default boxes for predictions.

SSD does not use a separate region proposal network; that is typical of two-stage detectors.

Explain how SSD detects objects in an image and why it is faster than two-stage detectors.

Think about how SSD predicts boxes and classes all at once.

Describe the purpose of default boxes and multi-scale feature maps in SSD.

Consider how SSD handles small and large objects.

Practice

1. What is the main advantage of the SSD (Single Shot MultiBox Detector) in object detection?

easy

A. It uses multiple passes to improve accuracy.

B. It detects objects in one pass, making it faster than some other methods.

C. It only detects one object per image.

D. It requires manual feature extraction before detection.

Solution

1. Step 1: Understand SSD's detection process

   SSD predicts object locations and classes in a single forward pass through the network, unlike methods that require multiple passes.

2. Step 2: Compare with other methods

   Methods like R-CNN use multiple passes, which are slower. SSD's single pass makes it faster for real-time use.

3. Final Answer:

   It detects objects in one pass, making it faster than some other methods. -> Option B

4. Quick Check:

   SSD speed = single pass detection [OK]

Hint: SSD = Single pass detection for speed [OK]

Common Mistakes:

• Thinking SSD uses multiple passes
• Believing SSD detects only one object
• Assuming manual feature extraction is needed

2. Which of the following is the correct description of SSD's output format?

easy

A. Multiple bounding boxes with class scores predicted in one pass.

B. A single class label for the whole image.

C. A heatmap showing object locations only.

D. A sequence of images with detected objects highlighted.

Solution

1. Step 1: Recall SSD output structure

   SSD outputs many bounding boxes with associated class probabilities in one forward pass.

2. Step 2: Eliminate incorrect options

   A single class label for the whole image is wrong because SSD predicts multiple objects, not one label. A heatmap showing object locations only is incorrect as SSD outputs boxes, not just heatmaps. A sequence of images with detected objects highlighted describes video or image sequence output, not SSD's prediction format.

3. Final Answer:

   Multiple bounding boxes with class scores predicted in one pass. -> Option A

4. Quick Check:

   SSD output = boxes + class scores [OK]

Hint: SSD outputs many boxes with classes at once [OK]

Common Mistakes:

• Confusing SSD output with single-label classifiers
• Thinking SSD outputs only heatmaps
• Assuming SSD outputs image sequences

3. Consider this simplified SSD output for one image:
boxes = [[0.1, 0.1, 0.4, 0.4], [0.5, 0.5, 0.9, 0.9]]
scores = [[0.9, 0.1], [0.2, 0.8]]
Here, each score list corresponds to [class0, class1]. Which box is predicted as class1 with higher confidence?

medium

A. The first box [0.1, 0.1, 0.4, 0.4]

B. Neither box predicts class1

C. Both boxes have equal confidence for class1

D. The second box [0.5, 0.5, 0.9, 0.9]

Solution

1. Step 1: Identify class1 scores for each box

   First box class1 score = 0.1, second box class1 score = 0.8.

2. Step 2: Compare scores to find higher confidence

   0.8 > 0.1, so second box has higher confidence for class1.

3. Final Answer:

   The second box [0.5, 0.5, 0.9, 0.9] -> Option D

4. Quick Check:

   Class1 highest score = 0.8 at second box [OK]

Hint: Check class1 scores, pick highest [OK]

Common Mistakes:

• Mixing class0 and class1 scores
• Ignoring score values and guessing
• Assuming equal confidence without checking

4. You have an SSD model that predicts many overlapping boxes for the same object. What common step should you add to fix this issue?

medium

A. Increase the learning rate during training.

B. Reduce the number of classes predicted.

C. Apply Non-Maximum Suppression (NMS) to remove overlapping boxes.

D. Use grayscale images instead of color.

Solution

1. Step 1: Understand overlapping box problem

   SSD often predicts multiple boxes around the same object, causing duplicates.

2. Step 2: Identify solution to remove duplicates

   Non-Maximum Suppression (NMS) filters overlapping boxes by keeping the one with highest confidence and removing others.

3. Final Answer:

   Apply Non-Maximum Suppression (NMS) to remove overlapping boxes. -> Option C

4. Quick Check:

   Overlapping boxes fix = NMS [OK]

Hint: Use NMS to clean overlapping boxes [OK]

Common Mistakes:

• Changing learning rate won't fix overlaps
• Reducing classes doesn't remove duplicates
• Switching image color doesn't affect box overlap

5. In a real-time traffic camera system using SSD, which combination of factors best balances speed and accuracy?

hard

A. Use SSD with a lightweight backbone network and moderate input image size.

B. Use SSD with a very deep backbone and very large input images.

C. Use SSD with no pre-trained weights and very small input images.

D. Use SSD with multiple passes over the image for better accuracy.

Solution

1. Step 1: Consider real-time constraints

   Real-time systems need fast processing, so a lightweight backbone helps speed up SSD.

2. Step 2: Balance input size and accuracy

   Moderate image size keeps enough detail for accuracy without slowing down processing too much.

3. Step 3: Evaluate other options

   Very deep backbones and large images slow down speed (Use SSD with a very deep backbone and very large input images.). No pre-training and very small images reduce accuracy (Use SSD with no pre-trained weights and very small input images.). Multiple passes slow down speed (Use SSD with multiple passes over the image for better accuracy.).

4. Final Answer:

   Use SSD with a lightweight backbone network and moderate input image size. -> Option A

5. Quick Check:

   Speed + accuracy = lightweight backbone + moderate size [OK]

Hint: Light backbone + moderate size = best speed-accuracy [OK]

Common Mistakes:

• Choosing very deep networks for real-time
• Using very small images losing accuracy
• Running multiple passes slows system