# CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency

Source: [CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency](<https://www.sota2.com/research/paper/68fa66e41e209131cea12e21>)

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

Data updated: 2025-10-25T22:00:21.133Z

Authors: Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, Jia-Bin Huang

Published: 2020-01-09T19:00:35.000Z

## Abstract

Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do not capture pixel-level domain shifts that are crucial for dense prediction tasks (e.g., semantic segmentation). In this paper, we present a novel pixel-wise adversarial domain adaptation algorithm. By leveraging image-to-image translation methods for data augmentation, our key insight is that while the translated images between domains may differ in styles, their predictions for the task should be consistent. We exploit this property and introduce a cross-domain consistency loss that enforces our adapted model to produce consistent predictions. Through extensive experimental results, we show that our method compares favorably against the state-of-the-art on a wide variety of unsupervised domain adaptation tasks.

## 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.

- [Semantic Segmentation on SYNTHIA to Cityscapes](<https://www.sota2.com/research/sota/semantic-segmentation-on-synthia-to-cityscapes.md>): Semantic segmentation; SYNTHIA to Cityscapes; Road IoU: 62.2.

- [Semantic Segmentation on SYNTHIA to Cityscapes (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-synthia-to-cityscapes-val.md>): Semantic segmentation; SYNTHIA to Cityscapes (val); Rider IoU: 15.9.

- [Semantic Segmentation on Cityscapes (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-cityscapes-val.md>): Semantic segmentation; Cityscapes (val); mIoU: 38.1.

- [Semantic Segmentation on GTA5 → Cityscapes (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-gta5-cityscapes-val.md>): Semantic segmentation; GTA5 → Cityscapes (val); mIoU: 38.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2001.03182>)

[PDF](<https://arxiv.org/pdf/2001.03182.pdf>)