# Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background

Source: [Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background](<https://www.sota2.com/research/paper/68fa74b01e209131cea6344b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:39:01.541Z

Authors: Biyuan Liu, Huaixin Chen, Huiyao Zhan, Sijie Luo, Zhou Huang

Published: 2024-09-01T02:48:11.000Z

## Abstract

Despite the eye-catching breakthroughs achieved by deep visual networks in detecting region-level surface defects, the challenge of high-quality pixel-wise defect detection remains due to diverse defect appearances and data scarcity. To avoid over-reliance on defect appearance and achieve accurate defect segmentation, we proposed a change-aware Siamese network that solves the defect segmentation in a change detection framework. A novel multi-class balanced contrastive loss is introduced to guide the Transformer-based encoder, which enables encoding diverse categories of defects as the unified class-agnostic difference between defect and defect-free images. The difference presented by a distance map is then skip-connected to the change-aware decoder to assist in the location of both inter-class and out-of-class pixel-wise defects. In addition, we proposed a synthetic dataset with multi-class liquid crystal display (LCD) defects under a complex and disjointed background context, to demonstrate the advantages of change-based modeling over appearance-based modeling for defect segmentation. In our proposed dataset and two public datasets, our model achieves superior performances than the leading semantic segmentation methods, while maintaining a relatively small model size. Moreover, our model achieves a new state-of-the-art performance compared to the semi-supervised approaches in various supervision settings.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.00589>)

[PDF](<https://arxiv.org/pdf/2409.00589.pdf>)
