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.
@article{arxiv.2201.12646,
title = {Self Semi Supervised Neural Architecture Search for Semantic Segmentation},
author = {Loïc Pauletto and Massih-Reza Amini and Nicolas Winckler},
journal= {arXiv preprint arXiv:2201.12646},
year = {2022}
}