CutMix对语义分割中可靠性与鲁棒性的影响
The Impact of CutMix on Reliability and Robustness in Semantic Segmentation
- Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院摄影测量与遥感研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究探究CutMix对语义分割的影响，发现其对分割准确率影响微小，但可提升模型可靠性，尤其在分布偏移场景下，增强的是校准度与不确定性可信度，对安全关键应用意义重大。
AI中文摘要：
在自动驾驶等安全关键应用中部署语义分割模型时，不仅要保证高准确率，还需获得可靠且鲁棒的预测结果，这一点至关重要。尽管CutMix作为一种简单却强大的数据增强策略已被广泛使用，但它对密集预测任务中可靠性与鲁棒性的影响仍未得到探究。鉴于近期研究发现以CutMix为核心组件的半监督分割方法会严重降低可靠性，本研究分离并系统分析了CutMix对分割准确率、校准度及不确定性质量的影响。我们评估了两种代表性架构：基于卷积神经网络的DeepLabV3+和基于Transformer的SegFormer，涵盖域内与域外两种场景。结果显示，CutMix对分割准确率仅产生微小影响，但始终能提升可靠性，尤其在分布偏移情况下表现明显。这些改进表明，CutMix主要提升的是模型校准度与不确定性的可信度，而非原始分割预测本身。这种区分对安全关键部署至关重要，因为可靠的置信度估计与原始性能同等重要。
英文摘要：
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.
