RoBiS: Robust Binary Segmentation for High-Resolution Industrial Images

TL;DR

RoBiS is a robust unsupervised anomaly detection framework for high-resolution industrial images, combining high-res pre-processing, data augmentation, adaptive binarization, and segmentation refinement to significantly improve detection accuracy.

Contribution

The paper introduces RoBiS, a novel framework that enhances anomaly detection in complex real-world industrial images through innovative pre-processing, augmentation, and adaptive segmentation techniques.

Findings

Achieves 29.2% SegF1 improvement on Test_private

Outperforms existing methods on MVTec AD 2 benchmark

Demonstrates robustness to real-world challenges

Abstract

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.