Metraipolis › archive › dc_cd2ba63c56c2
ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather — arXiv:2609.27533
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27533
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:34:54.971Z
- SHA-256 of the archived text
40c11be63aa908d2d4918b424d139d268363603d6633d24ddda1997f689ab948- Stable URL of this page
https://metraipolis.com/documento/dc_cd2ba63c56c2
How to cite
ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather — arXiv:2609.27533 — arXiv (en), https://arxiv.org/abs/2609.27533 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd2ba63c56c2 (Metraipolis archive dc_cd2ba63c56c2, sha256 40c11be63aa908d2d4918b424d139d268363603d6633d24ddda1997f689ab948)
BibTeX
@misc{dccd2ba63c56c2,
title = {ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather — arXiv:2609.27533},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27533},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd2ba63c56c2; sha256 40c11be63aa908d2d4918b424d139d268363603d6633d24ddda1997f689ab948},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27533. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.27533 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T12:12:35.695Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).