Self Semi Supervised Neural Architecture Search for Semantic Segmentation

TL;DR

This paper introduces a semi-supervised neural architecture search method for semantic segmentation that leverages self-supervision and unlabeled data to discover efficient neural network models, outperforming state-of-the-art hand-crafted models.

Contribution

It presents a novel NAS strategy combining self-supervised and semi-supervised learning, optimized via gradient descent, for semantic segmentation.

Findings

Discovered models are four times more efficient than existing hand-crafted models.

The approach achieves superior performance on Cityscapes and PASCAL VOC 2012 datasets.

The method effectively utilizes unlabeled data to improve segmentation accuracy.

Abstract

In this paper, we propose a Neural Architecture Search strategy based on self supervision and semi-supervised learning for the task of semantic segmentation. Our approach builds an optimized neural network (NN) model for this task by jointly solving a jigsaw pretext task discovered with self-supervised learning over unlabeled training data, and, exploiting the structure of the unlabeled data with semi-supervised learning. The search of the architecture of the NN model is performed by dynamic routing using a gradient descent algorithm. Experiments on the Cityscapes and PASCAL VOC 2012 datasets demonstrate that the discovered neural network is more efficient than a state-of-the-art hand-crafted NN model with four times less floating operations.