Model evaluation best practices in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Model evaluation best practices

Which metric matters and WHY

In computer vision, the right metric depends on the task. For image classification, accuracy shows how many images were correctly labeled. For object detection, precision and recall matter because you want to find all objects (high recall) but avoid false alarms (high precision). For segmentation, metrics like IoU (Intersection over Union) measure how well predicted shapes match real shapes. Choosing the right metric helps you understand if your model solves the problem well.

Confusion matrix example

      Confusion Matrix for Image Classification (3 classes):

           Predicted
           Cat  Dog  Bird
    Actual
    Cat    50    2     3
    Dog     4   45     1
    Bird    2    3    40

    Total samples = 150

    From this:
    - Accuracy = (50+45+40)/150 = 135/150 = 0.9 (90%)
    - Precision for Cat = TP/(TP+FP) = 50/(50+4+2) = 50/56 ≈ 0.89
    - Recall for Cat = TP/(TP+FN) = 50/(50+2+3) = 50/55 ≈ 0.91
    

Precision vs Recall tradeoff

Imagine a face recognition system unlocking your phone. You want high precision so it doesn't unlock for strangers (few false positives). But if it misses your face sometimes, that is okay (lower recall). On the other hand, a security camera detecting intruders needs high recall to catch all threats, even if it sometimes raises false alarms (lower precision). Understanding this tradeoff helps pick the right balance for your use case.

Good vs Bad metric values

Good metrics depend on the task. For example, in medical image diagnosis, a recall above 0.95 is good because missing a disease is dangerous. In a photo tagging app, an accuracy above 0.85 is good for user satisfaction. Bad metrics are low precision or recall, like precision below 0.5 means many wrong detections, or recall below 0.5 means many misses. Always compare metrics to your problem's needs.

Common pitfalls in model evaluation

• Accuracy paradox: High accuracy can be misleading if classes are imbalanced. For example, 95% accuracy on 95% background images means the model ignores rare objects.
• Data leakage: Using test images in training inflates metrics falsely.
• Overfitting: Very high training accuracy but low test accuracy means the model memorizes training images, not generalizing well.
• Ignoring metric context: Using only accuracy when recall matters can hide poor performance.

Self-check question

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

Answer: No, it is not good. The low recall means the model misses most rare objects, which could be critical. High accuracy is misleading here because most images do not have the rare object, so the model is mostly correct by saying "no object". Improving recall is essential.

Key Result

Choosing the right metric like precision, recall, or IoU is key to understanding if a computer vision model truly solves the task well.

Practice

1. Why is it important to use a separate test set when evaluating a computer vision model?

easy

A. To check how well the model performs on new, unseen data

B. To make the training process faster

C. To increase the size of the training data

D. To reduce the number of model parameters

Solution

1. Step 1: Understand the purpose of a test set

   The test set is data the model has never seen before, used to check real-world performance.

2. Step 2: Compare test set role with other options

   Options B, C, and D do not relate to evaluation but to training or model design.

3. Final Answer:

   To check how well the model performs on new, unseen data -> Option A

4. Quick Check:

   Test set = unseen data check [OK]

Hint: Test set = new data to check model accuracy [OK]

Common Mistakes:

• Confusing test set with training set
• Thinking test set speeds up training
• Believing test set changes model size

2. Which of the following is the correct way to split data for model evaluation in Python using scikit-learn?

easy

A. split_train_test(data, 0.2)

B. train_test_split(data, test_size=0.2, random_state=42)

C. train_test(data, 0.2)

D. test_train_split(data, 0.2)

Solution

1. Step 1: Recall the correct function name in scikit-learn

   The function to split data is called train_test_split with parameters like test_size and random_state.

2. Step 2: Check the options for correct syntax

   Only train_test_split(data, test_size=0.2, random_state=42) uses the correct function name and parameters; others are invalid or do not exist.

3. Final Answer:

   train_test_split(data, test_size=0.2, random_state=42) -> Option B

4. Quick Check:

   Correct function = train_test_split [OK]

Hint: Remember scikit-learn function: train_test_split [OK]

Common Mistakes:

• Using wrong function names
• Missing required parameters
• Confusing order of train and test

3. Given the following code snippet, what will be the printed accuracy?

from sklearn.metrics import accuracy_score
true_labels = [1, 0, 1, 1, 0]
pred_labels = [1, 0, 0, 1, 0]
accuracy = accuracy_score(true_labels, pred_labels)
print("{:.2f}".format(round(accuracy, 2)))

medium

A. 0.60

B. 0.40

C. 0.80

D. 1.00

Solution

1. Step 1: Compare true and predicted labels

   True: [1, 0, 1, 1, 0], Predicted: [1, 0, 0, 1, 0]. Matches at positions 0,1,3,4 (4 correct out of 5).

2. Step 2: Calculate accuracy

   Accuracy = correct predictions / total = 4/5 = 0.8. Rounded to 2 decimals is 0.80.

3. Final Answer:

   0.80 -> Option C

4. Quick Check:

   Accuracy = 4/5 = 0.80 [OK]

Hint: Count matches, divide by total labels [OK]

Common Mistakes:

• Counting wrong matches
• Not rounding accuracy
• Confusing accuracy with precision

4. You trained a model but the test accuracy is much higher than the training accuracy. What is the most likely issue?

medium

A. Data leakage between training and test sets

B. Model is underfitting the training data

C. Test set is too small

D. Training data is too large

Solution

1. Step 1: Understand unusual accuracy pattern

   Test accuracy higher than training is unusual and often means test data was seen during training.

2. Step 2: Identify cause from options

   Data leakage means test data accidentally used in training, causing inflated test accuracy.

3. Final Answer:

   Data leakage between training and test sets -> Option A

4. Quick Check:

   High test accuracy > training = data leakage [OK]

Hint: High test accuracy than train? Check data leakage [OK]

Common Mistakes:

• Assuming underfitting causes higher test accuracy
• Ignoring data leakage possibility
• Blaming test set size without evidence

5. You want to evaluate a computer vision model for detecting rare objects in images. Which evaluation metric is best to use and why?

hard

A. Confusion matrix, because it shows training time

B. Accuracy, because it shows overall correct predictions

C. Mean Squared Error, because it measures prediction error

D. F1 score, because it balances precision and recall for imbalanced data

Solution

1. Step 1: Understand the problem of rare object detection

   Rare objects mean data is imbalanced; many negatives, few positives.

2. Step 2: Choose metric suitable for imbalanced data

   F1 score balances precision (correct positive predictions) and recall (finding all positives), ideal for rare classes.

3. Final Answer:

   F1 score, because it balances precision and recall for imbalanced data -> Option D

4. Quick Check:

   Rare class? Use F1 score [OK]

Hint: Rare classes? Use F1 score for balance [OK]

Common Mistakes:

• Using accuracy which hides imbalance
• Confusing regression metrics with classification
• Misunderstanding confusion matrix purpose