# Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation

Source: [Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation](<https://www.sota2.com/research/paper/68fa6d031e209131cea3750a>)

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

Data updated: 2026-01-04T03:45:01.764Z

Authors: Zhengkai Jiang, Yuxi Li, Ceyuan Yang, Peng Gao, Yabiao Wang, Ying Tai, Chengjie Wang

Published: 2022-07-14T04:54:26.000Z

## Abstract

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient contrastive learning method for unsupervised domain adaptive semantic segmentation. Previous domain adaptation methods merely consider the alignment of the intra-class representational distributions across various domains, while the inter-class structural relationship is insufficiently explored, resulting in the aligned representations on the target domain might not be as easily discriminated as done on the source domain anymore. Instead, ProCA incorporates inter-class information into class-wise prototypes, and adopts the class-centered distribution alignment for adaptation. By considering the same class prototypes as positives and other class prototypes as negatives to achieve class-centered distribution alignment, ProCA achieves state-of-the-art performance on classical domain adaptation tasks, {\\em i.e., GTA5 $\\to$ Cityscapes \\text{and} SYNTHIA $\\to$ Cityscapes}. Code is available at \\href{https://github.com/jiangzhengkai/ProCA}{ProCA}

## 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 GTA5 → Cityscapes (val)](<https://www.sota2.com/research/sota/semantic-segmentation-on-gta5-cityscapes-val.md>): Semantic segmentation; GTA5 → Cityscapes (val); mIoU: 56.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.06654>)

[PDF](<https://arxiv.org/pdf/2207.06654.pdf>)