Pre-trained models (ResNet, VGG, EfficientNet) in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a pre-trained model in computer vision?

A pre-trained model is a neural network that has already been trained on a large dataset. It can be reused to solve similar tasks without training from scratch, saving time and resources.

intermediate

What is the main idea behind the ResNet architecture?

ResNet uses 'skip connections' or 'residual connections' that let the model learn differences from the input instead of the full transformation. This helps train very deep networks without losing information.

intermediate

How does VGG differ from ResNet in design?

VGG uses a simple and uniform design with many layers of small 3x3 filters stacked one after another. It does not use skip connections like ResNet but focuses on depth and simplicity.

advanced

What is special about EfficientNet compared to older models like VGG and ResNet?

EfficientNet scales the model's depth, width, and resolution together in a balanced way. This makes it more efficient, achieving better accuracy with fewer parameters and less computation.

beginner

Why do we use pre-trained models like ResNet, VGG, and EfficientNet in new computer vision tasks?

We use them to save time and improve performance. Since they learned useful features from large datasets, they help new models learn faster and better even with less data.

What is the key feature of ResNet that helps train very deep networks?

A Very large convolution filters

B Reducing the number of layers

C Using only fully connected layers

D Skip connections that add input to output

ResNet uses skip connections to let the network learn residuals, which helps avoid problems like vanishing gradients in deep networks.

Which model uses many small 3x3 convolution filters stacked deeply?

A VGG

B ResNet

C EfficientNet

D AlexNet

VGG is known for its simple design using many small 3x3 filters stacked in deep layers.

What does EfficientNet optimize to improve performance?

A Only depth of the network

B Only width of the network

C Depth, width, and resolution together

D Only resolution of input images

EfficientNet balances scaling depth, width, and input resolution to improve accuracy and efficiency.

Why are pre-trained models useful for new tasks?

A They require more data to train

B They start with learned features from large datasets

C They always have fewer layers

D They do not need any training

Pre-trained models have learned useful features from big datasets, so they help new tasks learn faster and better.

Which of these is NOT a characteristic of VGG?

A Use of skip connections

B Deep network with many layers

C Stacked 3x3 convolution layers

D Simple and uniform architecture

VGG does not use skip connections; that is a feature of ResNet.

Explain how ResNet's skip connections help in training deep neural networks.

Think about how adding input directly to output helps the network learn.

Describe the main differences between VGG and EfficientNet architectures.

Focus on design style and scaling approach.

Practice

1. Which of the following is a key advantage of using pre-trained models like ResNet, VGG, or EfficientNet in computer vision tasks?

easy

A. They reduce the size of the input images automatically.

B. They save training time by using knowledge from large datasets.

C. They only work for text data, not images.

D. They always require training from scratch for every new task.

Solution

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

   Pre-trained models are trained on large datasets and learn useful features that can be reused.

2. Step 2: Identify the benefit in context

   Using these models saves time because you don't need to train from scratch for every new task.

3. Final Answer:

   They save training time by using knowledge from large datasets. -> Option B

4. Quick Check:

   Pre-trained models save time = D [OK]

Hint: Pre-trained means already trained on big data [OK]

Common Mistakes:

• Thinking pre-trained models need full retraining
• Confusing image and text data applicability
• Assuming input size changes automatically

2. Which of the following is the correct way to load a pre-trained ResNet model in PyTorch?

easy

A. model = torch.load('resnet50')

B. model = torchvision.load_resnet50()

C. model = torchvision.models.ResNet50(weights='imagenet')

D. model = torchvision.models.resnet50(pretrained=True)

Solution

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

   In PyTorch, pre-trained models are loaded via torchvision.models with pretrained=True argument.

2. Step 2: Check each option

   model = torchvision.models.resnet50(pretrained=True) uses correct function and argument. Others are incorrect or invalid syntax.

3. Final Answer:

   model = torchvision.models.resnet50(pretrained=True) -> Option D

4. Quick Check:

   PyTorch pre-trained flag = pretrained=True [OK]

Hint: Use pretrained=True in torchvision.models [OK]

Common Mistakes:

• Using torch.load for model architecture
• Wrong function names like load_resnet50
• Incorrect argument names like weights='imagenet'

3. Consider this PyTorch code snippet using a pre-trained VGG16 model:

import torchvision.models as models
model = models.vgg16(pretrained=True)
print(type(model.features))

What will be the output type of model.features?

medium

A. <class 'torch.nn.Linear'>

B. <class 'torch.nn.ModuleList'>

C. <class 'torch.nn.Sequential'>

D. <class 'torch.nn.Conv2d'>

Solution

1. Step 1: Understand VGG16 model structure in PyTorch

   VGG16's feature extractor is implemented as a torch.nn.Sequential container of layers.

2. Step 2: Identify the type of model.features

   model.features groups convolutional layers in a Sequential module, so its type is torch.nn.Sequential.

3. Final Answer:

   <class 'torch.nn.Sequential'> -> Option C

4. Quick Check:

   VGG features = Sequential container [OK]

Hint: VGG features are in Sequential container [OK]

Common Mistakes:

• Confusing Sequential with ModuleList
• Thinking features is a single layer like Linear or Conv2d
• Not knowing PyTorch container types

4. You try to fine-tune a pre-trained EfficientNet model but get an error: AttributeError: module 'torchvision.models' has no attribute 'efficientnet'. What is the most likely cause?

medium

A. Your torchvision version is outdated and does not include EfficientNet.

B. You forgot to import torch.

C. EfficientNet models are not available in PyTorch.

D. You need to set pretrained=True to access EfficientNet.

Solution

1. Step 1: Understand the error message

   The error says torchvision.models has no attribute 'efficientnet', meaning the function is missing.

2. Step 2: Check common causes

   EfficientNet was added in newer torchvision versions. An outdated version lacks it.

3. Final Answer:

   Your torchvision version is outdated and does not include EfficientNet. -> Option A

4. Quick Check:

   Missing attribute = outdated torchvision [OK]

Hint: Check torchvision version for model availability [OK]

Common Mistakes:

• Assuming import torch fixes model availability
• Thinking EfficientNet is not in PyTorch at all
• Confusing pretrained flag with missing attribute

5. You want to build an image classifier for a small dataset with limited computing power. Which pre-trained model is the best choice to balance accuracy and efficiency?

hard

A. EfficientNet, because it scales well and is efficient for small data.

B. VGG16, because it is simple but very large and slow.

C. ResNet50, because it is very deep and accurate but heavy.

D. Train a new model from scratch for best results.

Solution

1. Step 1: Consider dataset size and computing power

   Small data and limited power require efficient models to avoid overfitting and long training.

2. Step 2: Compare model characteristics

   ResNet50 is accurate but heavy; VGG16 is large and slow; EfficientNet is designed for efficiency and good accuracy.

3. Step 3: Choose the best fit

   EfficientNet balances accuracy and efficiency, making it ideal for small datasets and limited resources.

4. Final Answer:

   EfficientNet, because it scales well and is efficient for small data. -> Option A

5. Quick Check:

   Efficiency + accuracy = EfficientNet [OK]

Hint: EfficientNet balances speed and accuracy well [OK]

Common Mistakes:

• Choosing heavy models for small data
• Ignoring efficiency for limited computing power
• Thinking training from scratch is always better