# Ablation study of self-supervised learning for image classification

Source: [Ablation study of self-supervised learning for image classification](<https://www.sota2.com/research/paper/68fa6b5d1e209131cea2daaf>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:46:07.580Z

Authors: Ilias Papastratis

Published: 2021-12-04T09:59:01.000Z

## Abstract

This project focuses on the self-supervised training of convolutional neural networks (CNNs) and transformer networks for the task of image recognition. A simple siamese network with different backbones is used in order to maximize the similarity of two augmented transformed images from the same source image. In this way, the backbone is able to learn visual information without supervision. Finally, the method is evaluated on three image recognition datasets.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2112.02297>)

[PDF](<https://arxiv.org/pdf/2112.02297.pdf>)