Investigating a Baseline Of Self Supervised Learning Towards Reducing Labeling Costs For Image Classification
This work addresses the high cost of data labeling for supervised learning in image classification, but it is incremental as it establishes a baseline rather than introducing new methods.
This study tackled the problem of reducing labeling costs in image classification by investigating how much labeled data is needed for self-supervised learning to achieve competent accuracy. Results showed that pretext pre-training in self-supervised learning improved accuracy by around 15% compared to plain supervised learning on datasets like cats-vs-dogs, MNIST, and Fashion-MNIST.
Data labeling in supervised learning is considered an expensive and infeasible tool in some conditions. The self-supervised learning method is proposed to tackle the learning effectiveness with fewer labeled data, however, there is a lack of confidence in the size of labeled data needed to achieve adequate results. This study aims to draw a baseline on the proportion of the labeled data that models can appreciate to yield competent accuracy when compared to training with additional labels. The study implements the kaggle.com' cats-vs-dogs dataset, Mnist and Fashion-Mnist to investigate the self-supervised learning task by implementing random rotations augmentation on the original datasets. To reveal the true effectiveness of the pretext process in self-supervised learning, the original dataset is divided into smaller batches, and learning is repeated on each batch with and without the pretext pre-training. Results show that the pretext process in the self-supervised learning improves the accuracy around 15% in the downstream classification task when compared to the plain supervised learning.