Abstract

Unsupervised domain adaptation (UDA) for semantic segmentation remains challenging under adverse weather conditions because severe appearance changes enlarge the domain gap and degrade the reliability of pseudo labels in the target domain. To address this problem, we propose an Intra-Class Mixing Consistency (ICM) framework that enforces prediction consistency between an intra-class mixed image and its original counterpart. Unlike previous mixing-based consistency methods that combine regions across different images or domains and may introduce unrealistic semantic inconsistencies, ICM performs mixing within the same image and semantic class, preserving realistic semantic layout for consistency regularization. With ICM, we establish a new state-of-the-art performance for clear-to-adverse-weather unsupervised domain adaptation (UDA) in semantic segmentation. On the Cityscapes $\rightarrow$ ACDC benchmark, our method achieves 75.7\% mIoU, outperforming the previous state of the art by +1.9 pp, demonstrating its effectiveness in mitigating class confusion under challenging environmental conditions. The code is provided in the supplementary material.

Keywords

Subject

Publication details

Journal
Not available
Open access
Green open access

Cite this article

APA 7

Li, B., Liu, C., Wilde, B. A., Kovács, G., Adewumi, T., Backe, B., & Mokayed, H. (2026). ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather. https://omanscience.com/en/articles/icm-intra-class-mixing-for-domain-adaptation-in-adverse-weather

MLA 9

Li, Boying, et al. "ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather." https://omanscience.com/en/articles/icm-intra-class-mixing-for-domain-adaptation-in-adverse-weather.

Chicago (author–date)

Li, Boying, Chang Liu, Britta Ayano Wilde, György Kovács, Tosin Adewumi, Björn Backe, and Hamam Mokayed. 2026. "ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather." https://omanscience.com/en/articles/icm-intra-class-mixing-for-domain-adaptation-in-adverse-weather.

Harvard

Li, B., Liu, C., Wilde, B. A., Kovács, G., Adewumi, T., Backe, B. and Mokayed, H. (2026) 'ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather', Available at: https://omanscience.com/en/articles/icm-intra-class-mixing-for-domain-adaptation-in-adverse-weather.

Vancouver

Li B, Liu C, Wilde BA, Kovács G, Adewumi T, Backe B, et al. ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather. https://omanscience.com/en/articles/icm-intra-class-mixing-for-domain-adaptation-in-adverse-weather

IEEE

B. Li, C. Liu, B. A. Wilde, G. Kovács, T. Adewumi, B. Backe, and H. Mokayed, "ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather," https://omanscience.com/en/articles/icm-intra-class-mixing-for-domain-adaptation-in-adverse-weather.