Spatial Transformer Networks for Curriculum Learning
This work addresses the challenge of automating task difficulty progression in curriculum learning for neural network training, though it is incremental as it applies an existing method (STNs) to a new context.
The paper tackled the problem of generating simpler tasks for curriculum learning by using Spatial Transformer Networks (STNs) to process images as easier tasks, resulting in a 3.8 percentage point improvement in classification accuracy on the cluttered MNIST dataset compared to the baseline.
Curriculum learning is a bio-inspired training technique that is widely adopted to machine learning for improved optimization and better training of neural networks regarding the convergence rate or obtained accuracy. The main concept in curriculum learning is to start the training with simpler tasks and gradually increase the level of difficulty. Therefore, a natural question is how to determine or generate these simpler tasks. In this work, we take inspiration from Spatial Transformer Networks (STNs) in order to form an easy-to-hard curriculum. As STNs have been proven to be capable of removing the clutter from the input images and obtaining higher accuracy in image classification tasks, we hypothesize that images processed by STNs can be seen as easier tasks and utilized in the interest of curriculum learning. To this end, we study multiple strategies developed for shaping the training curriculum, using the data generated by STNs. We perform various experiments on cluttered MNIST and Fashion-MNIST datasets, where on the former, we obtain an improvement of $3.8$pp in classification accuracy compared to the baseline.