用遗传算法生成逼真干扰，让分割模型更抗扰。
Evaluating and Enhancing Segmentation Model Robustness with Metamorphic Testing
- 用遗传算法优化图像变换序列，保持清晰度。
- 使DeepLabV3的mIoU降至6.4%，优于其他方法。
- 可用于训练，提升模型在对抗数据上的表现。
图像分割在医学成像、增强现实和视频监控中至关重要，但分割模型常因细微图像失真而脆弱。本文提出SegRMT，一种基于遗传算法（GA）的变异测试方法，在保持预设PSNR阈值的前提下，优化空间与光谱变换序列，生成对抗性样本。在Cityscapes数据集上，该方法使DeepLabV3模型的均值交并比（mIoU）降至6.4%，优于其他基线方法（8.5%~21.7%）。此外，用于对抗训练时，可使模型在专用对抗数据集上的mIoU提升高达73%，跨对抗场景下mIoU达53.8%，远超其他方法（仅2%-10%）。结果表明，SegRMT不仅能模拟真实图像失真，还能有效提升分割模型鲁棒性，适用于安全关键应用中的可靠性保障。
原文摘要 · Abstract (English)
Image segmentation is critical for applications such as medical imaging, augmented reality, and video surveillance. However, segmentation models often lack robustness, making them vulnerable to adversarial perturbations from subtle image distortions. In this work, we propose SegRMT, a metamorphic testing approach that leverages genetic algorithms (GA) to optimize sequences of spatial and spectral transformations while preserving image fidelity via a predefined PSNR threshold. Using the Cityscapes dataset, our method generates adversarial examples that effectively challenge the DeepLabV3 segmentation model. Our experiments show that SegRMT reduces DeepLabV3's mean Intersection over Union (mIoU) to 6.4%, outperforming other adversarial baselines that decrease mIoU to between 8.5% and 21.7%. Furthermore, when used for adversarial training, SegRMT boosts model performance, achieving mIoU improvements up to 73% on dedicated adversarial datasets and increasing cross-adversarial mIoU to 53.8%, compared to only 2%-10% for other methods. These findings demonstrate that SegRMT not only simulates realistic image distortions but also enhances the robustness of segmentation models, making it a valuable tool for ensuring reliable performance in safety-critical applications.
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。