# Consistency Regularization for Domain Adaptation

Source: [Consistency Regularization for Domain Adaptation](<https://www.sota2.com/research/paper/68fa6d501e209131cea390f5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:31:24.160Z

Authors: Kian Boon Koh, Basura Fernando

Published: 2022-08-23T17:07:06.000Z

## Abstract

Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic data can be used to train and adapt models to real world images without requiring their annotations. Recent UDA methods applies self-learning by training on pixel-wise classification loss using a student and teacher network. In this paper, we propose the addition of a consistency regularization term to semi-supervised UDA by modelling the inter-pixel relationship between elements in networks' output. We demonstrate the effectiveness of the proposed consistency regularization term by applying it to the state-of-the-art DAFormer framework and improving mIoU19 performance on the GTA5 to Cityscapes benchmark by 0.8 and mIou16 performance on the SYNTHIA to Cityscapes benchmark by 1.2.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2208.11084>)

[PDF](<https://arxiv.org/pdf/2208.11084.pdf>)