Improving Semantic Segmentation via Self-Training

04/30/2020
by   Yi Zhu, et al.
8

Deep learning usually achieves the best results with complete supervision. In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models. In this paper, we show that we can obtain state-of-the-art results using a semi-supervised approach, specifically a self-training paradigm. We first train a teacher model on labeled data, and then generate pseudo labels on a large set of unlabeled data. Our robust training framework can digest human-annotated and pseudo labels jointly and achieve top performances on Cityscapes, CamVid and KITTI datasets while requiring significantly less supervision. We also demonstrate the effectiveness of self-training on a challenging cross-domain generalization task, outperforming conventional finetuning method by a large margin. Lastly, to alleviate the computational burden caused by the large amount of pseudo labels, we propose a fast training schedule to accelerate the training of segmentation models by up to 2x without performance degradation.

READ FULL TEXT

page 2

page 15

page 22

page 23

page 24

page 26

research
09/15/2022

Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

Self-training has shown great potential in semi-supervised learning. Its...
research
01/18/2023

Semi-Supervised Semantic Segmentation via Gentle Teaching Assistant

Semi-Supervised Semantic Segmentation aims at training the segmentation ...
research
05/20/2022

UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation

Deep neural networks (DNNs) have witnessed great successes in semantic s...
research
12/15/2021

Self-Ensembling GAN for Cross-Domain Semantic Segmentation

Deep neural networks (DNNs) have greatly contributed to the performance ...
research
12/15/2022

Urban Scene Semantic Segmentation with Low-Cost Coarse Annotation

For best performance, today's semantic segmentation methods use large an...
research
10/30/2019

Auto-Annotation Quality Prediction for Semi-Supervised Learning with Ensembles

Auto-annotation by ensemble of models is an efficient method of learning...
research
03/31/2021

The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation

We consider the task of semi-supervised semantic segmentation, where we ...

Please sign up or login with your details

Forgot password? Click here to reset