Pre-trained detection models in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Pre-trained detection models

Which metric matters for Pre-trained detection models and WHY

For pre-trained detection models, the key metrics are Precision, Recall, and F1 score. These models find objects in images, so we want to know how many detected objects are correct (Precision) and how many real objects were found (Recall). The F1 score balances both. Also, mean Average Precision (mAP) is often used to measure overall detection quality across classes and thresholds.

Confusion matrix for object detection (simplified)

      | Predicted Object  | Predicted No Object |
      |------------------|---------------------|
      | True Positive (TP)| False Negative (FN)  |
      | False Positive (FP)| True Negative (TN)  |

    TP: Correctly detected objects
    FP: Wrong detections (false alarms)
    FN: Missed objects
    TN: Correctly ignored background
    

Precision = TP / (TP + FP)

Recall = TP / (TP + FN)

Precision vs Recall tradeoff with examples

If the model is very strict, it detects fewer objects but with high confidence. This means high precision but low recall. For example, in security cameras, you want to avoid false alarms (high precision).

If the model detects many objects, including uncertain ones, it has high recall but low precision. For example, in wildlife monitoring, missing an animal is worse, so high recall is preferred.

The F1 score helps balance these two depending on the use case.

What "good" vs "bad" metric values look like for pre-trained detection models

Good: Precision and Recall both above 0.8, F1 score near 0.85 or higher, and mAP above 0.75. This means the model finds most objects correctly and misses few.

Bad: Precision below 0.5 means many false detections. Recall below 0.5 means many missed objects. Low F1 and mAP indicate poor detection quality.

Common pitfalls in metrics for pre-trained detection models

• Accuracy paradox: High accuracy can be misleading if most images have no objects (TN dominate).
• Data leakage: Using test images in training inflates metrics falsely.
• Overfitting: Very high training metrics but low test metrics show poor generalization.
• Ignoring IoU threshold: Detection quality depends on Intersection over Union threshold; metrics vary with it.

Self-check question

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

Answer: No, it is not good. The high accuracy is misleading because most images may not have cars, so the model correctly predicts no car often (TN). The very low recall means it misses most cars, which is bad for detection tasks where finding objects is critical.

Key Result

Precision, Recall, and mAP are key metrics to evaluate how well pre-trained detection models find and correctly identify objects.

Practice

1. What is the main advantage of using a pre-trained detection model in computer vision?

easy

A. It allows detecting objects without needing to train the model from scratch.

B. It guarantees 100% accuracy on all images.

C. It requires no input images to work.

D. It only works for detecting faces.

Solution

1. Step 1: Understand what pre-trained models do

   Pre-trained detection models are trained on large datasets and can detect objects without retraining.

2. Step 2: Compare options with this fact

   It allows detecting objects without needing to train the model from scratch. correctly states the main advantage: no need to train from scratch. Other options are incorrect or too specific.

3. Final Answer:

   It allows detecting objects without needing to train the model from scratch. -> Option A

4. Quick Check:

   Pre-trained means ready-to-use without training [OK]

Hint: Pre-trained means ready to use without training [OK]

Common Mistakes:

• Thinking pre-trained models always have perfect accuracy
• Believing pre-trained models need no images
• Assuming pre-trained models detect only one object type

2. Which of the following is the correct way to load a pre-trained object detection model using PyTorch's torchvision library?

easy

A. model = torchvision.models.detection.load('fasterrcnn_resnet50_fpn', pretrained=True)

B. model = torchvision.load_model('fasterrcnn_resnet50_fpn')

C. model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)

D. model = torchvision.models.fasterrcnn_resnet50_fpn()

Solution

1. Step 1: Recall PyTorch torchvision syntax for pre-trained detection models

   The correct method is to call the model constructor with pretrained=True argument.

2. Step 2: Check each option

   model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True) matches the correct syntax. Options A and B use invalid functions. model = torchvision.models.fasterrcnn_resnet50_fpn() misses pretrained=True, so model is untrained.

3. Final Answer:

   model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True) -> Option C

4. Quick Check:

   Use model constructor with pretrained=True [OK]

Hint: Use model constructor with pretrained=True to load model [OK]

Common Mistakes:

• Using nonexistent functions like load_model or load
• Forgetting pretrained=True argument
• Calling model without detection namespace

3. Given the following code snippet using a pre-trained detection model, what will be the output type of outputs?

import torchvision
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()
inputs = [image_tensor]
outputs = model(inputs)

medium

A. A list of dictionaries, each containing detected boxes, labels, and scores.

B. A single tensor with class predictions only.

C. A dictionary with keys 'boxes' and 'labels' only.

D. A list of image tensors with detected objects cropped.

Solution

1. Step 1: Understand output format of torchvision detection models

   These models return a list of dictionaries, one per input image, with keys like 'boxes', 'labels', and 'scores'.

2. Step 2: Match output type with options

   A list of dictionaries, each containing detected boxes, labels, and scores. correctly describes this output. Other options describe incorrect or incomplete formats.

3. Final Answer:

   A list of dictionaries, each containing detected boxes, labels, and scores. -> Option A

4. Quick Check:

   Detection model outputs list of dicts with boxes, labels, scores [OK]

Hint: Detection outputs are list of dicts with boxes, labels, scores [OK]

Common Mistakes:

• Expecting a single tensor instead of list
• Missing 'scores' key in output
• Thinking output crops images automatically

4. You try to run a pre-trained detection model but get the error: RuntimeError: Expected 4-dimensional input. What is the most likely cause?

medium

A. The model was not loaded with pretrained weights.

B. The input image tensor is missing the batch dimension.

C. The input image is grayscale instead of RGB.

D. The model is in training mode instead of evaluation mode.

Solution

1. Step 1: Understand input shape requirements for detection models

   Detection models expect input tensors with shape [batch_size, channels, height, width], i.e., 4 dimensions.

2. Step 2: Identify cause of 4D input error

   If input lacks batch dimension (only 3D), this error occurs. The input image tensor is missing the batch dimension. matches this cause. Other options do not cause this error.

3. Final Answer:

   The input image tensor is missing the batch dimension. -> Option B

4. Quick Check:

   Input must have batch dimension (4D tensor) [OK]

Hint: Add batch dimension to input tensor to fix 4D error [OK]

Common Mistakes:

• Ignoring batch dimension requirement
• Confusing pretrained loading with input shape
• Assuming grayscale causes dimension error

5. You want to use a pre-trained detection model to detect cars and people only. Which approach is best to adapt the model's output for this task?

hard

A. Use the model without any filtering; it will detect only cars and people automatically.

B. Retrain the entire model from scratch with only car and person images.

C. Modify the model architecture to remove other classes before loading weights.

D. Filter the model's detected labels to keep only 'car' and 'person' classes after prediction.

Solution

1. Step 1: Understand pre-trained model adaptation options

   Pre-trained models detect many classes. To focus on some, filtering outputs is easiest and fastest.

2. Step 2: Evaluate each option

   Filter the model's detected labels to keep only 'car' and 'person' classes after prediction. filters predictions after detection, which is practical. Retrain the entire model from scratch with only car and person images. is costly retraining. Modify the model architecture to remove other classes before loading weights. is complex and not standard. Use the model without any filtering; it will detect only cars and people automatically. is incorrect; model detects all classes by default.

3. Final Answer:

   Filter the model's detected labels to keep only 'car' and 'person' classes after prediction. -> Option D

4. Quick Check:

   Filter outputs to select desired classes [OK]

Hint: Filter detection results to keep only needed classes [OK]

Common Mistakes:

• Thinking retraining is always needed
• Trying to change model architecture directly
• Assuming model detects only desired classes by default