CutMix虽对分割精度影响小，却显著提升模型可靠性与鲁棒性。
The Impact of CutMix on Reliability and Robustness in Semantic Segmentation
- 通过隔离分析CutMix在密集预测中的作用，对比不同架构表现。
- 在分布外场景下，CutMix使模型校准度和不确定性质量明显提升。
- 适合关注安全关键应用中模型可信度的开发者参考。
在自动驾驶等安全关键场景中，确保语义分割模型不仅高精度，还需具备可靠且鲁棒的预测能力至关重要。尽管CutMix作为一种简单而强大的数据增强策略被广泛使用，其对密集预测任务中可靠性与鲁棒性的影响尚未明确。受近期研究发现——半监督分割方法中以CutMix为核心时可能严重降低可靠性——启发，本研究系统分析了CutMix对分割精度、校准性和不确定性质量的影响。评估了基于CNN的DeepLabV3+与基于Transformer的SegFormer两种代表性架构，在域内与域外场景下的表现。结果表明，CutMix对分割精度仅有轻微影响，但能持续提升模型可靠性，尤其在分布偏移情况下。这说明CutMix主要增强了模型的校准可信度与不确定性估计能力，而非原始分割性能。这一区分对安全关键部署至关重要，因可靠的置信度估计与性能同等重要。
原文摘要 · Abstract (English)
Ensuring not only high accuracy but also reliable and robust predictions is critical for the deployment of semantic segmentation models in safety-critical applications such as autonomous driving. Despite the widespread use of CutMix - a simple yet powerful data augmentation strategy - its effect on the reliability and robustness in dense predictions tasks remains unexplored. Motivated by recent findings that semi-supervised segmentation methods, where CutMix is a core component, can severely degrade reliability, this study isolates and systematically analyzes the influence of CutMix on segmentation accuracy, calibration, and uncertainty quality. We evaluate two representative architectures, the CNN-based DeepLabV3+ and the transformer-based SegFormer, across both in-domain and out-of-domain scenarios. Our results show that CutMix has only a minor impact on segmentation accuracy but consistently improves the reliability, particularly under distribution shifts. These improvements indicate that CutMix primarily enhances the trustworthiness of the model's calibration and uncertainty rather than the raw segmentation prediction itself. This distinction is crucial for safety-critical deployment, where reliable confidence estimates are as important as raw performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。