Self-supervised Neural Architecture Search

07/03/2020
by   Sapir Kaplan, et al.
0

Neural Architecture Search (NAS) has been used recently to achieve improved performance in various tasks and most prominently in image classification. Yet, current search strategies rely on large labeled datasets, which limit their usage in the case where only a smaller fraction of the data is annotated. Self-supervised learning has shown great promise in training neural networks using unlabeled data. In this work, we propose a self-supervised neural architecture search (SSNAS) that allows finding novel network models without the need for labeled data. We show that such a search leads to comparable results to supervised training with a "fully labeled" NAS and that it can improve the performance of self-supervised learning. Moreover, we demonstrate the advantage of the proposed approach when the number of labels in the search is relatively small.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/15/2022

Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning

Recently, Neural Architecture Search (NAS) methods have been introduced ...
research
02/21/2021

Contrastive Self-supervised Neural Architecture Search

This paper proposes a novel cell-based neural architecture search algori...
research
09/17/2021

Self-Supervised Neural Architecture Search for Imbalanced Datasets

Neural Architecture Search (NAS) provides state-of-the-art results when ...
research
01/29/2022

Self Semi Supervised Neural Architecture Search for Semantic Segmentation

In this paper, we propose a Neural Architecture Search strategy based on...
research
04/03/2023

Self-Supervised learning for Neural Architecture Search (NAS)

The objective of this internship is to propose an innovative method that...
research
07/13/2021

Tourbillon: a Physically Plausible Neural Architecture

In a physical neural system, backpropagation is faced with a number of o...
research
10/31/2020

Self-supervised Representation Learning for Evolutionary Neural Architecture Search

Recently proposed neural architecture search (NAS) algorithms adopt neur...

Please sign up or login with your details

Forgot password? Click here to reset