Pre-trained detection models in Computer Vision - Model Pipeline Trace

Model Pipeline - Pre-trained detection models

This pipeline uses a pre-trained detection model to find objects in images. It takes an image, processes it, and outputs boxes around detected objects with labels and confidence scores.

Data Flow - 6 Stages

1Input Image

1 image x 640 x 480 x 3 channels→Load and resize image to fixed size→1 image x 640 x 480 x 3 channels

A photo of a street with cars and people

↓

2Preprocessing

1 image x 640 x 480 x 3 channels→Normalize pixel values to 0-1 range→1 image x 640 x 480 x 3 channels

Pixel values changed from 0-255 to 0.0-1.0

↓

3Feature Extraction

1 image x 640 x 480 x 3 channels→Pass image through convolutional layers of pre-trained backbone→1 feature map x 40 x 30 x 512 channels

Extracted edges and shapes like wheels and faces

↓

4Region Proposal

1 feature map x 40 x 30 x 512 channels→Generate candidate boxes where objects might be→1000 candidate boxes x 4 coordinates

Boxes around possible cars, people, signs

↓

5Classification and Refinement

1000 candidate boxes x 4 coordinates→Classify each box and adjust box size→Top 100 boxes with class labels and confidence scores

Box #23 labeled 'car' with 0.92 confidence

↓

6Non-Maximum Suppression

Top 100 boxes with labels and scores→Remove overlapping boxes to keep best ones→Final 10 boxes with labels and confidence

One box per detected car or person

Training Trace - Epoch by Epoch

Loss
2.5 |*       
2.0 | *      
1.5 |  *     
1.0 |   *    
0.5 |    **  
0.0 +---------
      1 5 10 15 20 Epochs

Epoch	Loss ↓	Accuracy ↑	Observation
1	2.5	0.30	Model starts learning basic object features
5	1.2	0.55	Model improves detecting common objects
10	0.8	0.70	Model refines box predictions and labels
15	0.5	0.82	Model converges with good detection accuracy
20	0.45	0.85	Minor improvements, stable performance

Prediction Trace - 6 Layers

Layer 1: Input Image

Layer 2: Preprocessing

Layer 3: Feature Extraction

Layer 4: Region Proposal

Layer 5: Classification and Refinement

Layer 6: Non-Maximum Suppression

Model Quiz - 3 Questions

What is the main purpose of the region proposal stage?

A To suggest possible object locations in the image

B To classify objects into categories

C To normalize pixel values

D To resize the input image

Key Insight

Pre-trained detection models speed up object detection by using learned features from large datasets. They propose many possible object locations, classify them, and then keep only the best boxes to accurately detect objects in new images.

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