Domain adaptation method improves segmentation in bad weather
ICM: Intra-class Mixing for Domain Adaptation in Adverse Weather
Computer Vision and Pattern Recognition
Summary
Semantic segmentation is a way for computers to understand images by identifying each part of a scene. This task gets harder in bad weather because the images look very different, making the computer confused. The authors created a new method called intra-class mixing consistency (ICM), which mixes parts of the same object within an image to help the computer learn better without confusing different things. Their method improved accuracy on a well-known test for understanding images taken in bad weather, showing it helps computers see more clearly when conditions are tough.
What this means in practice
- •For autonomous vehicle teams: Improve self-driving car perception systems by better adapting from clear weather training data to adverse weather conditions for safer navigation.$Commercial implications: Enables companies to sell more reliable autonomous driving systems that work well in challenging weather, a major safety requirement.
- •For smart city infrastructure teams: Enhance visual monitoring systems to maintain accurate scene understanding under varying and adverse weather conditions without additional labeling.
Authors
Boying Li, Chang Liu, Britta Ayano Wilde, György Kovács, Tosin Adewumi, Björn Backe, Hamam Mokayed
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.