LGCVAug 17, 2021

Investigating a Baseline Of Self Supervised Learning Towards Reducing Labeling Costs For Image Classification

arXiv:2108.07464v13 citations
Originality Synthesis-oriented
AI Analysis

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes