# A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm

Source: [A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm](<https://www.sota2.com/research/paper/68fa671f1e209131cea14685>)

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

Data updated: 2025-10-25T22:07:19.924Z

Authors: Sungwon Han, Yizhan Xu, Sungwon Park, Meeyoung Cha, Cheng-Te Li

Published: 2020-02-26T13:22:04.000Z

## Abstract

Unsupervised embedding learning aims to extract good representation from data without the need for any manual labels, which has been a critical challenge in many supervised learning tasks. This paper proposes a new unsupervised embedding approach, called Super-AND, which extends the current state-of-the-art model. Super-AND has its unique set of losses that can gather similar samples nearby within a low-density space while keeping invariant features intact against data augmentation. Super-AND outperforms all existing approaches and achieves an accuracy of 89.2% on the image classification task for CIFAR-10. We discuss the practical implications of this method in assisting semi-supervised tasks.

## 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/2002.12158>)

[PDF](<https://arxiv.org/pdf/2002.12158.pdf>)