ResNet and skip connections in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main problem ResNet aims to solve in deep neural networks?

ResNet addresses the problem of vanishing gradients and degradation in very deep networks, where adding more layers makes training harder and accuracy worse.

beginner

What is a skip connection in ResNet?

A skip connection is a shortcut that bypasses one or more layers by directly adding the input of those layers to their output, helping gradients flow better during training.

intermediate

How does a skip connection help during backpropagation?

Skip connections allow gradients to flow directly through the shortcut, reducing the chance of gradients becoming too small and enabling easier training of deep networks.

intermediate

In ResNet, what is the typical operation performed when combining the input and output in a skip connection?

The input is added element-wise to the output of the stacked layers, forming a residual block output: output = F(input) + input.

intermediate

Why are ResNet models often deeper than traditional CNNs?

Because skip connections help avoid training problems like vanishing gradients, ResNet can safely add many more layers, improving feature learning and accuracy.

What problem do skip connections in ResNet primarily address?

A Batch normalization

B Vanishing gradients

C Data augmentation

D Overfitting

Skip connections help gradients flow better, solving the vanishing gradient problem in deep networks.

In a ResNet residual block, how is the output computed?

A Output = F(input) + input

B Output = input * F(input)

C Output = F(input) - input

D Output = input / F(input)

The residual block output is the sum of the input and the function F(input) from the layers.

Why can ResNet have hundreds of layers without training issues?

A Because it uses dropout

B Because it uses small batch sizes

C Because of skip connections

D Because it uses ReLU activation only

Skip connections allow gradients to flow easily, enabling very deep networks to train well.

What does the 'F' represent in the ResNet formula output = F(input) + input?

A The identity function

B The input data

C The loss function

D The residual mapping learned by the layers

F is the function learned by the stacked layers in the residual block.

Which of these is NOT a benefit of skip connections?

A Increasing model overfitting

B Reduced training time

C Avoiding vanishing gradients

D Improved gradient flow

Skip connections help training but do not cause overfitting; they improve model learning.

Explain in your own words what a skip connection is and why it helps deep neural networks.

Think about how information flows in a network and what happens when it can skip some layers.

Describe the structure of a ResNet residual block and how it differs from a traditional convolutional block.

Focus on the addition operation and the shortcut path.

Practice

1. What is the main purpose of skip connections in a ResNet model?

easy

A. To replace convolutional layers with fully connected layers

B. To reduce the number of layers in the network

C. To allow information to flow directly across layers, helping training

D. To increase the size of the input images

Solution

1. Step 1: Understand skip connections role

   Skip connections let the input bypass some layers and add directly to the output, helping information flow.

2. Step 2: Connect to training deep networks

   This helps avoid problems like vanishing gradients, making training deep networks easier and more accurate.

3. Final Answer:

   To allow information to flow directly across layers, helping training -> Option C

4. Quick Check:

   Skip connections improve training by direct flow [OK]

Hint: Skip connections let info skip layers to ease training [OK]

Common Mistakes:

• Thinking skip connections reduce layers
• Confusing skip connections with input size changes
• Assuming skip connections replace convolution

2. Which of the following is the correct way to add a skip connection in PyTorch between input tensor x and output tensor out?

easy

A. out = x - out

B. out = x * out

C. out = x / out

D. out = x + out

Solution

1. Step 1: Recall skip connection operation

   Skip connections add the input tensor to the output tensor element-wise.

2. Step 2: Match with correct syntax

   The addition operation out = x + out correctly implements the skip connection.

3. Final Answer:

   out = x + out -> Option D

4. Quick Check:

   Skip connection = addition [OK]

Hint: Skip connections use addition, not multiplication or division [OK]

Common Mistakes:

• Using multiplication instead of addition
• Using subtraction or division which breaks skip connection
• Confusing order of operands

3. Consider this PyTorch code snippet for a ResNet block:

import torch
import torch.nn as nn

class SimpleResBlock(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(3, 3, kernel_size=3, padding=1)
        self.relu = nn.ReLU()
        self.conv.weight.data.fill_(0.0)
        self.conv.bias.data.fill_(1.0)

    def forward(self, x):
        out = self.conv(x)
        out = self.relu(out)
        out = out + x
        return out

block = SimpleResBlock()
input_tensor = torch.ones(1, 3, 5, 5)
output = block(input_tensor)
print(output[0,0,0,0].item())

What will be printed?

medium

A. 2.0

B. 1.0

C. 0.0

D. An error occurs

Solution

1. Step 1: Analyze convolution output

   The convolution with kernel size 3 and padding 1 keeps the input size. Since input is all ones, convolution output will be some positive values (not zero).

2. Step 2: Add input and apply ReLU

   ReLU keeps positive values. Then adding input tensor (all ones) increases values. So output values > 1.

3. Final Answer:

   2.0 -> Option A

4. Quick Check:

   Output = conv + input > 1 [OK]

Hint: Skip connection adds input, so output > input value [OK]

Common Mistakes:

• Assuming output equals input without addition
• Ignoring padding effect on size
• Expecting zero or error due to shape mismatch

4. You wrote this PyTorch code for a ResNet block but get a runtime error:

def forward(self, x):
    out = self.conv(x)
    out = self.relu(out)
    out = out + x
    return out

The error says: "The size of tensor a (64) must match the size of tensor b (128) at non-singleton dimension 1." What is the likely cause?

medium

A. The convolution changes the number of channels, so shapes don't match for addition

B. ReLU changes tensor shape unexpectedly

C. Input tensor is None

D. The addition operator is used incorrectly

Solution

1. Step 1: Understand error message

   The error says channel sizes differ (64 vs 128), so tensors can't be added element-wise.

2. Step 2: Check convolution output channels

   If convolution changes channels from 64 to 128, input and output shapes differ, causing addition error.

3. Final Answer:

   The convolution changes the number of channels, so shapes don't match for addition -> Option A

4. Quick Check:

   Channel mismatch causes addition error [OK]

Hint: Check channel sizes before adding tensors [OK]

Common Mistakes:

• Blaming ReLU for shape errors
• Ignoring channel dimension mismatch
• Assuming addition works regardless of shape

5. In a ResNet architecture, if the input tensor has shape (batch_size, 64, 32, 32) and the convolution layer in the block changes channels to 128 with stride 2, how can you correctly implement the skip connection?

hard

A. Add input tensor directly without changes

B. Use a 1x1 convolution with stride 2 on the input to match shape before addition

C. Use max pooling on output tensor before addition

D. Skip connection is not needed in this case

Solution

1. Step 1: Identify shape mismatch

   Input has 64 channels and size 32x32; output has 128 channels and size 16x16 due to stride 2.

2. Step 2: Match shapes for addition

   To add tensors, input must be transformed to 128 channels and 16x16 size, done by 1x1 convolution with stride 2.

3. Final Answer:

   Use a 1x1 convolution with stride 2 on the input to match shape before addition -> Option B

4. Quick Check:

   Match shape with 1x1 conv before skip add [OK]

Hint: Use 1x1 conv to match shape for skip connection [OK]

Common Mistakes:

• Adding tensors with different shapes directly
• Using pooling on output instead of input
• Skipping skip connection when channels differ