Image Classification using Single Class Dataset using Transfer Learning

Question

I only have around 1000 images of vehicle. I need to train a model that can identify if the image is vehicle or not-vehicle. I do not have a dataset for not-vehicle, as it could be anything besides vehicle.

I guess the best method for this would be to apply transfer learning. I am trying to train data on a pre-trained VGG19 Model. But still, I am unaware on how to train a model with just vehicle images without any non-vehicle images. I am not being able to classify it.

I am new to ML Overall, Any solution based on practical implementation will be highly appreciated.

Answer 1

You are right about transfer learning approach. Have a look a this article, it is exactly about going from multi-class to binary classification with transfer learning - https://medium.com/@mandygu/seefood-creating-a-binary-classifier-using-transfer-learning-da751db7cf9c

Answer 2

This is a binary classification problem: whether the input is a vehicle or not.

If you are new to ML, I would suggest you should start implementing basic binary classifiers like Logistic Regression, Support Vector Machines before jumping to Convolutional Neural Networks (CNNs). I am providing some links for the binary classification problem implementations using different algorithms. I hope this would help.

Logistic Regression: https://github.com/JB1984/Logistic-Regression-Cat-Classifier

SVM: https://github.com/Witsung/SVM-Fruit-Image-Classifier

CNN: https://github.com/A-Jatin/CNN-implementation-for-binary-image-classification

Answer 3

You can try using pretrained model and take the output. You might need to apply dimensionality reduction e.g. PCA, to get a more managable size input. After that you can train novelty detection model to identify whether the output is different than your training set.

Refer to this example: https://github.com/J-Yash/Hotdog-Not-Hotdog

Hope this helps.