Pre-trained detection models in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Understanding Pre-trained Detection Models

What is the main advantage of using a pre-trained object detection model instead of training one from scratch?

A It requires less labeled data and less training time to achieve good accuracy.

B It guarantees perfect accuracy on any new dataset without further training.

C It eliminates the need for any data preprocessing before inference.

D It only works for detecting objects in black and white images.

💡 Hint

Think about the resources needed to train a model from zero versus using a model already trained on a large dataset.

Pre-trained models have already learned useful features from large datasets, so they need less data and time to adapt to new tasks.

❓ Predict Output

intermediate

Output of Pre-trained Model Inference Code

What is the output of this Python code snippet using a pre-trained detection model from torchvision?

Computer Vision

import torch
from torchvision.models.detection import fasterrcnn_resnet50_fpn
model = fasterrcnn_resnet50_fpn(pretrained=True)
model.eval()

# Dummy input: batch of 1 image with 3 channels, 224x224 pixels
input_tensor = torch.randn(1, 3, 224, 224)
outputs = model(input_tensor)
print(type(outputs))

A <class 'dict'>

B <class 'tuple'>

C <class 'torch.Tensor'>

D <class 'list'>

💡 Hint

Check the documentation for torchvision detection models' output format.

Pre-trained detection models in torchvision return a list of dictionaries, one per image in the batch.

❓ Model Choice

advanced

Choosing a Pre-trained Detection Model for Real-Time Use

You want to deploy an object detection model on a mobile device with limited computing power and need real-time performance. Which pre-trained model is the best choice?

A Faster R-CNN with ResNet-50 backbone

B YOLOv5 Nano version

C Mask R-CNN with ResNet-101 backbone

D RetinaNet with ResNet-152 backbone

💡 Hint

Consider model size and speed for mobile deployment.

YOLOv5 Nano is designed for fast inference on low-resource devices, unlike heavier models like Faster R-CNN or Mask R-CNN.

❓ Hyperparameter

advanced

Adjusting Confidence Threshold in Pre-trained Detection Models

When using a pre-trained detection model, what is the effect of increasing the confidence threshold parameter during inference?

A The model retrains itself to improve accuracy automatically.

B More detected objects are shown, including many false positives.

C Fewer detected objects are shown, but with higher confidence in each detection.

D The input image resolution is increased to improve detection quality.

💡 Hint

Think about filtering detections based on how sure the model is.

Increasing the confidence threshold filters out low-confidence detections, reducing false positives but possibly missing some true objects.

❓ Metrics

expert

Evaluating Pre-trained Detection Model Performance

You evaluate a pre-trained object detection model on a test set and get these results: precision = 0.75, recall = 0.60. What does this tell you about the model's detections?

A The model is good at avoiding false alarms but misses many true objects.

B The model detects most true objects but has many false alarms.

C The model has perfect detection with no errors.

D The model's predictions are random and unreliable.

💡 Hint

Recall measures how many true objects are found; precision measures how many detections are correct.

Precision of 0.75 means 75% of detections are correct; recall of 0.60 means 40% of true objects are missed.

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