Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper tackles the problem of poor generalization in semantic segmentation of outdoor scenes under adverse weather conditions. They demonstrate that a carefully designed training recipe, focused on data augmentation and sampling strategies, can significantly reduce the validation-test gap compared to simply increasing model capacity. Their approach, using a SegMAN-S backbone and techniques like domain-adaptive fine-tuning and scene-balanced sampling, achieves a 59.9% mIoU on the test set with a much smaller generalization gap than larger models like SegFormer-B5.
Forget bigger models: a smart training recipe slashes the generalization gap in adverse weather segmentation by more than half.
This paper describes our approach for the 8th UG2+ Workshop (CVPR 2026) Track~2, which targets semantic segmentation of outdoor scenes degraded by five weather conditions: blur, darkness, snow, haze, and glare. A central challenge we observe is a severe generalization gap -- models that perform well on the validation set often collapse on the test set. For instance, SegFormer-B5 drops 16.1 mIoU points from validation to test, suggesting that model capacity alone is insufficient for robustness. We investigate whether a carefully designed training recipe, rather than architectural complexity, can address this gap. Starting from a pre-trained SegMAN-S backbone, we systematically study the effects of domain-adaptive fine-tuning, multi-source data mixing, scene-balanced sampling, and synthetic degradation augmentation. Our final system achieves 59.9\% mIoU on the official test set while maintaining a validation-test gap of only 6.5 points -- less than half that of larger models. We analyze negative results from architectural modifications, loss function variants, and model scaling to provide practical insights for weather-robust segmentation under limited data.