Why detection localizes objects in images in Computer Vision - Why Metrics Matter

Metrics & Evaluation - Why detection localizes objects in images

Which metric matters for this concept and WHY

In object detection, the key metric is Intersection over Union (IoU). It measures how well the predicted box matches the true object box. A higher IoU means the model localizes the object more accurately. Along with IoU, mean Average Precision (mAP) is used to evaluate both detection and localization quality together. These metrics matter because detection is not just about saying "there is an object" but also showing exactly where it is in the image.

Confusion matrix or equivalent visualization (ASCII)

True Positive (TP): Correctly detected and localized objects (IoU > threshold)
False Positive (FP): Detected boxes with no matching true object or low IoU
False Negative (FN): True objects missed by the detector

Example confusion matrix for detection:

           | Detected Object | No Detection |
-----------|-----------------|--------------|
Object     |       TP        |      FN      |
No Object  |       FP        |      TN      |

Note: TN (True Negative) is less meaningful in detection because the background is large.
    

Precision vs Recall tradeoff with concrete examples

Precision means when the model says "object here," it is usually right. High precision means few false alarms.

Recall means the model finds most of the objects present. High recall means few missed objects.

For example, in self-driving cars, missing a pedestrian (low recall) is dangerous, so recall is critical. But too many false alarms (low precision) can also confuse the system.

Balancing precision and recall depends on the use case. IoU thresholds affect this balance: a higher IoU threshold demands more accurate localization, which can lower recall but improve precision.

What "good" vs "bad" metric values look like for this use case

Good detection model:

• IoU > 0.5 for most detected objects
• High mAP (e.g., > 0.7) showing good detection and localization
• Precision and recall both above 0.8, meaning few false alarms and few misses

Bad detection model:

• Low IoU (e.g., < 0.3) meaning boxes do not match objects well
• Low mAP (e.g., < 0.4) indicating poor detection or localization
• High false positives (low precision) or many missed objects (low recall)

Metrics pitfalls

• Accuracy paradox: In images with few objects, a model that predicts no objects can have high accuracy but is useless.
• Ignoring IoU: Counting detections without checking localization quality can mislead about model performance.
• Data leakage: Testing on images very similar to training can inflate metrics falsely.
• Overfitting: Very high training mAP but low test mAP means the model memorizes training images, not generalizing.

Self-check question

Your object detection model has 98% accuracy but only 12% recall on detecting pedestrians. Is it good for production? Why or why not?

Answer: No, it is not good. The high accuracy is misleading because most of the image is background (no pedestrians). The very low recall means the model misses almost all pedestrians, which is dangerous especially in safety-critical applications like self-driving cars.

Key Result

IoU and mAP are key metrics showing how well detection models find and localize objects accurately.

Practice

1. Why does object detection localize objects in images?

easy

A. To find both what the object is and where it is located

B. To only classify the object without location

C. To change the colors of the image

D. To remove objects from the image

Solution

1. Step 1: Understand the purpose of detection

   Detection aims to identify objects and their positions in an image, not just what they are.

2. Step 2: Differentiate detection from classification

   Classification only tells what object is present, but detection also tells where it is by drawing boxes.

3. Final Answer:

   To find both what the object is and where it is located -> Option A

4. Quick Check:

   Detection = What + Where [OK]

Hint: Detection = object type + location in image [OK]

Common Mistakes:

• Confusing detection with classification
• Thinking detection changes image colors
• Believing detection removes objects

2. Which output format correctly represents object detection results?

easy

A. Only a label without any location

B. A label and a bounding box with coordinates

C. A list of pixel colors

D. A blurred version of the image

Solution

1. Step 1: Identify detection output components

   Detection outputs include the object label and a bounding box showing where the object is.

2. Step 2: Eliminate incorrect outputs

   Labels alone or pixel colors do not localize objects; blurring is unrelated.

3. Final Answer:

   A label and a bounding box with coordinates -> Option B

4. Quick Check:

   Detection output = label + box [OK]

Hint: Detection outputs label + box, not just label [OK]

Common Mistakes:

• Thinking detection outputs only labels
• Confusing detection output with image filters
• Ignoring bounding box coordinates

3. Given this detection output: {'label': 'cat', 'box': [50, 30, 150, 130], 'confidence': 0.9}, what does the box represent?

medium

A. The number of cats detected

B. The color values of the cat

C. The size of the image

D. Coordinates of the cat's bounding box in the image

Solution

1. Step 1: Understand the box format

   The box is a list of four numbers representing coordinates (x1, y1, x2, y2) of the bounding box around the object.

2. Step 2: Interpret the meaning of the box

   This box shows where the cat is located in the image, not color or image size.

3. Final Answer:

   Coordinates of the cat's bounding box in the image -> Option D

4. Quick Check:

   Box = object location coordinates [OK]

Hint: Box = coordinates marking object location [OK]

Common Mistakes:

• Confusing box with color or size
• Thinking box counts objects
• Ignoring coordinate meaning

4. A detection model outputs boxes but they do not match object locations well. What is a likely cause?

medium

A. The model was not trained with enough labeled bounding boxes

B. The image resolution is too high

C. The model only classifies objects without localization

D. The image is in grayscale

Solution

1. Step 1: Identify training data impact

   Detection models need many labeled bounding boxes to learn accurate localization.

2. Step 2: Rule out unrelated factors

   High resolution or grayscale images do not directly cause poor box accuracy; classification-only models do not output boxes at all.

3. Final Answer:

   The model was not trained with enough labeled bounding boxes -> Option A

4. Quick Check:

   Training data quality affects box accuracy [OK]

Hint: Poor boxes? Check training bounding boxes quantity [OK]

Common Mistakes:

• Blaming image resolution instead of training data
• Confusing classification with detection
• Ignoring training data quality

5. In a safety monitoring system, why is it important that detection localizes objects instead of just classifying them?

hard

A. Because localization removes objects from images

B. Because classification alone can change object colors

C. Because knowing object locations helps track movements and avoid hazards

D. Because classification is slower than localization

Solution

1. Step 1: Understand safety system needs

   Safety systems need to know where objects are to monitor movement and prevent accidents.

2. Step 2: Compare classification vs localization

   Classification only tells what objects are present, but localization tells where they are, which is critical for tracking.

3. Final Answer:

   Because knowing object locations helps track movements and avoid hazards -> Option C

4. Quick Check:

   Safety needs location info, not just labels [OK]

Hint: Safety needs object location, not just type [OK]

Common Mistakes:

• Thinking classification changes colors
• Believing localization removes objects
• Confusing speed differences