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.