Why CNNs dominate image classification in Computer Vision

Introduction

CNNs are great at finding patterns in pictures. They look at small parts of images and combine what they learn to understand the whole picture.

When you want a computer to recognize objects in photos, like cats or cars.

When sorting pictures into groups, such as different types of flowers.

When detecting faces or expressions in images for apps.

When improving photo search by understanding image content.

When building apps that need to read handwritten numbers or letters.

Syntax

Computer Vision

import torch
import torch.nn as nn
import torch.nn.functional as F

class SimpleCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3)
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(16 * 6 * 6, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        return x

CNNs use layers called convolutional layers to scan images piece by piece.

Pooling layers help reduce image size while keeping important info.

Examples

This creates a convolutional layer for grayscale images with 8 filters.

Computer Vision

conv_layer = nn.Conv2d(in_channels=1, out_channels=8, kernel_size=3)

This layer shrinks the image by taking the biggest value in each 2x2 area.

Computer Vision

pool_layer = nn.MaxPool2d(kernel_size=2, stride=2)

This is a fully connected layer that outputs 10 class scores.

Computer Vision

fc_layer = nn.Linear(in_features=128, out_features=10)

Sample Model

This code builds a simple CNN that looks at 28x28 grayscale images and outputs scores for 2 classes. It shows how CNN layers work together.

Computer Vision

import torch
import torch.nn as nn
import torch.nn.functional as F

class SimpleCNN(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = nn.Conv2d(1, 4, 3)  # 1 input channel (grayscale), 4 filters
        self.pool = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(4 * 13 * 13, 2)  # assuming input 28x28

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        return x

# Create a dummy batch of 2 grayscale images 28x28
inputs = torch.randn(2, 1, 28, 28)

model = SimpleCNN()
outputs = model(inputs)
print("Output shape:", outputs.shape)
print("Output values:", outputs)

Important Notes

CNNs automatically learn important features from images without manual work.

They reduce the number of parameters compared to regular neural networks, making training easier.

Pooling layers help CNNs focus on important parts and ignore small shifts in images.

Summary

CNNs scan images in small parts to find patterns.

Pooling helps shrink images while keeping key info.

This makes CNNs very good and popular for image tasks.

Practice

1. Why are Convolutional Neural Networks (CNNs) especially good for image classification?

easy

A. Because they only work with black and white images

B. Because they use random guessing to classify images

C. Because they ignore image details and focus on text

D. Because they scan small parts of images to find important patterns

Solution

1. Step 1: Understand CNN scanning method

   CNNs look at small parts of an image called patches to detect patterns like edges or shapes.

2. Step 2: Connect scanning to image classification

   By scanning patches, CNNs learn important features that help tell one image from another.

3. Final Answer:

   Because they scan small parts of images to find important patterns -> Option D

4. Quick Check:

   CNN scanning = small parts pattern detection [OK]

Hint: Remember CNNs focus on small image parts to find patterns [OK]

Common Mistakes:

• Thinking CNNs guess randomly
• Believing CNNs ignore image details
• Assuming CNNs only work on black and white images

2. Which of the following is the correct way to describe the pooling operation in CNNs?

easy

A. Pooling increases the image size to add more details

B. Pooling shrinks the image while keeping important information

C. Pooling removes all colors from the image

D. Pooling randomly changes pixel values

Solution

1. Step 1: Define pooling in CNNs

   Pooling reduces the size of the image or feature map but keeps the key features intact.

2. Step 2: Identify correct description

   Pooling does not increase size or remove colors; it shrinks the image while preserving important info.

3. Final Answer:

   Pooling shrinks the image while keeping important information -> Option B

4. Quick Check:

   Pooling = shrink + keep key info [OK]

Hint: Pooling shrinks images but keeps what matters [OK]

Common Mistakes:

• Thinking pooling makes images bigger
• Believing pooling removes colors
• Assuming pooling changes pixels randomly

3. Given this simple CNN layer code snippet in Python using PyTorch:

import torch
import torch.nn as nn
conv = nn.Conv2d(in_channels=3, out_channels=1, kernel_size=3)
input_tensor = torch.randn(1, 3, 5, 5)
output = conv(input_tensor)
print(output.shape)

What will be the shape of the output tensor?

medium

A. torch.Size([1, 1, 3, 3])

B. torch.Size([1, 3, 3, 3])

C. torch.Size([1, 1, 5, 5])

D. torch.Size([3, 1, 3, 3])

Solution

1. Step 1: Understand Conv2d output size formula

   Output size = (Input size - Kernel size + 1) for default stride and padding. Here, input is 5x5, kernel is 3x3, so output is 3x3.

2. Step 2: Check channels and batch size

   Batch size is 1, output channels is 1, so output shape is (1, 1, 3, 3).

3. Final Answer:

   torch.Size([1, 1, 3, 3]) -> Option A

4. Quick Check:

   Output shape = (1, 1, 3, 3) [OK]

Hint: Output size = input - kernel + 1 with default stride [OK]

Common Mistakes:

• Confusing input and output channels
• Forgetting batch size dimension
• Assuming output size equals input size

4. Identify the error in this CNN pooling layer code snippet:

import torch
import torch.nn as nn
pool = nn.MaxPool2d(kernel_size=2, stride=3)
input_tensor = torch.randn(1, 1, 6, 6)
output = pool(input_tensor)
print(output.shape)

What is the problem with this code?

medium

A. Input tensor shape is invalid for pooling

B. Kernel size must be equal to stride in MaxPool2d

C. Stride is larger than kernel size, causing unexpected output size

D. MaxPool2d does not accept stride as a parameter

Solution

1. Step 1: Check pooling parameters

   Stride can be different from kernel size, but stride larger than kernel size can cause skipping regions and smaller output.

2. Step 2: Understand effect on output size

   Stride 3 with kernel 2 on 6x6 input reduces output size more than expected, which may cause loss of important info.

3. Final Answer:

   Stride is larger than kernel size, causing unexpected output size -> Option C

4. Quick Check:

   Stride > kernel size affects output size [OK]

Hint: Stride bigger than kernel skips image parts, watch output size [OK]

Common Mistakes:

• Thinking kernel size must equal stride
• Believing input shape is invalid
• Assuming MaxPool2d can't take stride

5. You want to build a CNN that classifies images of cats and dogs. Which combination best explains why CNNs dominate this task compared to a simple fully connected network?

hard

A. CNNs scan local image parts and use pooling to reduce size, capturing patterns efficiently

B. Fully connected networks scan images in small parts and pool features

C. CNNs ignore image patterns and rely on random weights

D. Fully connected networks use convolution layers to find edges

Solution

1. Step 1: Compare CNN and fully connected networks

   CNNs scan small parts of images (local receptive fields) and use pooling to keep important info while reducing size.

2. Step 2: Understand why CNNs are better for images

   Fully connected networks treat all pixels equally without spatial structure, making them less efficient for images.

3. Final Answer:

   CNNs scan local image parts and use pooling to reduce size, capturing patterns efficiently -> Option A

4. Quick Check:

   CNN local scan + pooling > fully connected for images [OK]

Hint: CNNs scan parts + pool; fully connected treats all pixels equally [OK]

Common Mistakes:

• Confusing fully connected with convolution layers
• Thinking CNNs ignore image patterns
• Believing fully connected networks use pooling