# Bidirectional Learning for Domain Adaptation of Semantic Segmentation

## TL;DR

This paper introduces a bidirectional learning framework that enhances domain adaptation for semantic segmentation by mutually improving image translation and segmentation models through an iterative, self-supervised approach, outperforming existing methods.

## Contribution

The paper presents a novel bidirectional learning framework that jointly optimizes image translation and segmentation adaptation models for improved domain adaptation performance.

## Key findings

- Outperforms state-of-the-art domain adaptation methods
- Effective self-supervised learning algorithm for segmentation
- Significant performance improvement in experiments

## Abstract

Domain adaptation for semantic image segmentation is very necessary since manually labeling large datasets with pixel-level labels is expensive and time consuming. Existing domain adaptation techniques either work on limited datasets, or yield not so good performance compared with supervised learning. In this paper, we propose a novel bidirectional learning framework for domain adaptation of segmentation. Using the bidirectional learning, the image translation model and the segmentation adaptation model can be learned alternatively and promote to each other. Furthermore, we propose a self-supervised learning algorithm to learn a better segmentation adaptation model and in return improve the image translation model. Experiments show that our method is superior to the state-of-the-art methods in domain adaptation of segmentation with a big margin. The source code is available at https://github.com/liyunsheng13/BDL.