提升高分辨率工业图像异常检测鲁棒性，精度显著超越现有方法。
RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images
- 通过重叠窗口裁剪保留小异常信息，增强高分辨率图像处理能力。
- 在训练数据中加入噪声与光照扰动，提升模型对真实场景的适应性。
- 融合统计与自适应二值化策略，结合SAM优化分割结果，适合工业质检场景。
真实场景中的无监督异常检测至关重要，但现有方法在MVTec AD 2基准上因复杂现实挑战导致性能严重下降。为此，我们提出稳健框架RoBiS，包含三个核心模块：(1) Swin-Cropping，一种高分辨率图像预处理策略，通过重叠窗口裁剪保留小异常信息；(2) 在训练数据中添加噪声和模拟光照变化，提升模型鲁棒性；以INP-Former为基线，在各子图像上生成更优结果；(3) 将传统统计二值化（均值+3倍标准差）与我们之前工作MEBin（CVPR2025发表）联合用于自适应二值化，并进一步使用SAM精修分割结果。相比部分已报道的MVTec AD 2方法，RoBiS在Test_private上实现SegF1提升29.2%（从21.8%增至51.00%），在Test_private_mixed上提升29.82%（从16.7%增至46.52%）。代码已开源：https://github.com/xrli-U/RoBiS。
原文摘要 · Abstract (English)
Robust unsupervised anomaly detection (AD) in real-world scenarios is an important task. Current methods exhibit severe performance degradation on the MVTec AD 2 benchmark due to its complex real-world challenges. To solve this problem, we propose a robust framework RoBiS, which consists of three core modules: (1) Swin-Cropping, a high-resolution image pre-processing strategy to preserve the information of small anomalies through overlapping window cropping. (2) The data augmentation of noise addition and lighting simulation is carried out on the training data to improve the robustness of AD model. We use INP-Former as our baseline, which could generate better results on the various sub-images. (3) The traditional statistical-based binarization strategy (mean+3std) is combined with our previous work, MEBin (published in CVPR2025), for joint adaptive binarization. Then, SAM is further employed to refine the segmentation results. Compared with some methods reported by the MVTec AD 2, our RoBiS achieves a 29.2% SegF1 improvement (from 21.8% to 51.00%) on Test_private and 29.82% SegF1 gains (from 16.7% to 46.52%) on Test_private_mixed. Code is available at https://github.com/xrli-U/RoBiS.
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。