# LowDINO -- A Low Parameter Self Supervised Learning Model

Source: [LowDINO -- A Low Parameter Self Supervised Learning Model](<https://www.sota2.com/research/paper/68fa6f791e209131cea45d33>)

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

Data updated: 2025-10-26T01:21:27.030Z

Authors: Sai Krishna Prathapaneni, Shvejan Shashank, Srikar Reddy K

Published: 2023-05-28T18:34:59.000Z

## Abstract

This research aims to explore the possibility of designing a neural network architecture that allows for small networks to adopt the properties of huge networks, which have shown success in self-supervised learning (SSL), for all the downstream tasks like image classification, segmentation, etc. Previous studies have shown that using convolutional neural networks (ConvNets) can provide inherent inductive bias, which is crucial for learning representations in deep learning models. To reduce the number of parameters, attention mechanisms are utilized through the usage of MobileViT blocks, resulting in a model with less than 5 million parameters. The model is trained using self-distillation with momentum encoder and a student-teacher architecture is also employed, where the teacher weights use vision transformers (ViTs) from recent SOTA SSL models. The model is trained on the ImageNet1k dataset. This research provides an approach for designing smaller, more efficient neural network architectures that can perform SSL tasks comparable to heavy models

## 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/2305.17791>)

[PDF](<https://arxiv.org/pdf/2305.17791.pdf>)
