CBAM-SwinT-BL：基于块级CBAM增强的Swin Transformer的小型钢轨表面缺陷检测方法
CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement
AI总结：
本文提出CBAM-SwinT-BL，通过在Swin Transformer块内逐级集成CBAM增强小尺寸钢轨表面缺陷检测，在RIII与MUET数据集上显著提升mAP-50和总体精度，且训练开销很小。
摘要：
在高强度钢轨运营下，钢轨轨道承受相当大的应力，导致波磨和剥落等各类缺陷。若未能有效检测缺陷并及时进行维护，将损害运营可靠性和公共安全。尽管近年来已开发出先进模型，但高效识别小规模钢轨缺陷尚未得到研究，尤其是针对钢轨表面的Dirt（污垢）或Squat（鞍形擦伤）等类别。为应对这一挑战，本研究以Swin Transformer（SwinT）为基线，并引入卷积块注意力模块（Convolutional Block Attention Module，CBAM）进行增强。所提方法将CBAM依次集成到Swin Transformer块内部，从而在钢轨缺陷检测中取得显著性能提升，尤其是对于实例尺寸较小的类别。所提出的框架命名为块级CBAM增强Swin Transformer（CBAM-Enhanced Swin Transformer in Block Level，CBAM-SwinT-BL）。实验和消融研究证明了该框架的有效性。所提框架在小尺寸缺陷的精度上有显著提升，例如RIII数据集中的dirt和dent类别，mAP-50分别提升了+23.0%和+38.3%；MUET数据集中的squat类别也比原始模型提高+13.2%。与原始SwinT相比，CBAM-SwinT-BL在MUET数据集上的总体精度提高约+5%，在RIII数据集上提高约+7%，分别达到69.1%和88.1%。同时，附加的CBAM模块仅使模型训练速度平均增加+0.04秒/迭代，相较于系统性能的显著提升，这一代价是可接受的。
英文摘要：
Under high-intensity rail operations, rail tracks endure considerable stresses resulting in various defects such as corrugation and spellings. Failure to effectively detect defects and provide maintenance in time would compromise service reliability and public safety. While advanced models have been developed in recent years, efficiently identifying small-scale rail defects has not yet been studied, especially for categories such as Dirt or Squat on rail surface. To address this challenge, this study utilizes Swin Transformer (SwinT) as baseline and incorporates the Convolutional Block Attention Module (CBAM) for enhancement. Our proposed method integrates CBAM successively within the swin transformer blocks, resulting in significant performance improvement in rail defect detection, particularly for categories with small instance sizes. The proposed framework is named CBAM-Enhanced Swin Transformer in Block Level (CBAM-SwinT-BL). Experiment and ablation study have proven the effectiveness of the framework. The proposed framework has a notable improvement in the accuracy of small size defects, such as dirt and dent categories in RIII dataset, with mAP-50 increasing by +23.0% and +38.3% respectively, and the squat category in MUET dataset also reaches +13.2% higher than the original model. Compares to the original SwinT, CBAM-SwinT-BL increase overall precision around +5% in the MUET dataset and +7% in the RIII dataset, reaching 69.1% and 88.1% respectively. Meanwhile, the additional module CBAM merely extend the model training speed by an average of +0.04s/iteration, which is acceptable compared to the significant improvement in system performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
