CNN With unbalanced Data

Hello

I have a question regarding CNN in MATLAB

I have a dataset with imbalanced classes. 70 for A 20 for B and 10 for C. How can I reduce the effect of this imbalance during training. The input images are binary images

When performing a leave-one-out scheme, the prediction is mostly going to be A every time.

The network archetecture am using is the exact same as AlexNet network

image_size = 512;
layers = [
    imageInputLayer([image_size image_size 1],'Normalization','none')
    
    convolution2dLayer(11,96,'Stride',4,'Padding',0)
    reluLayer
    crossChannelNormalizationLayer(5)
    
    maxPooling2dLayer(3,'Stride',2)
   
    groupedConvolution2dLayer(5,128,2,'Stride',1,'Padding',2)
    reluLayer
    crossChannelNormalizationLayer(5)
    
    maxPooling2dLayer(3,'Stride',2)

    convolution2dLayer(3,384,'Stride',1,'Padding',1)
    reluLayer
    
    groupedConvolution2dLayer(3,192,2,'Stride',1,'Padding',1)
    reluLayer

    groupedConvolution2dLayer(3,128,2,'Stride',1,'Padding',1)
    reluLayer
    
    maxPooling2dLayer(3,'Stride',2)
    
    fullyConnectedLayer(4096)
    reluLayer
    dropoutLayer(0.5)
    
    fullyConnectedLayer(4096)
    reluLayer
    dropoutLayer(0.5)
    
    fullyConnectedLayer(3,'WeightLearnRateFactor',1,'BiasLearnRateFactor',1)
    softmaxLayer
    classificationLayer];

% analyzeNetwork(layers)

options = trainingOptions('sgdm',...
    'ExecutionEnvironment','gpu',...
    'Minibatchsize',10,...
    'MaxEpochs',64,...
    'InitialLearnRate',0.0001,...
    'Shuffle','every-epoch',...
    'Verbose',false,...
    'Plots','training-progress');

My main question is how to make the network predicting the other two classes as well instead of just shooting for A because it is the highest amount of data. Is there a command to use or something wrong with the network?

I do not prefer data augmentation for the dataset am using as the shape and size are important factors.

Thank you

Answer 1

[Greg Heath]

Although you do not prefer data augmentation, duplication of the smaller dataset examples is probably the quickest and most reliable way to proceed.

Thank you for formally accepting my answer.

Greg

[Mohanad Alkhodari]

Since I am using Binary images, the shape is important between the three classes. They are not images of creatures, they are shapes or patterns. Augmentation will mix up the shapes right? Is this a prefered approach for this example?

[Greg Heath]

???

Duplication is not augmetation!

Greg

[Mohanad Alkhodari]

https://www.mathworks.com/help/deeplearning/ref/augmentedimagedatastore.html

Is this example of what you are refering to for augmentation?

Could you please suggest an approach for augmentation in this imbalanced dataset?

[Kenta]

This is an example code for oversampling. https://jp.mathworks.com/matlabcentral/fileexchange/78020-oversampling-for-deep-learning-classification-example

This may help you.