mlsanityData to 14 Oct 2026

CBAM-SwinT-BL: Small Rail Surface Defect Detection Method Based on Swin Transformer with Block Level CBAM Enhancement

arXiv 2409.20113 ↗First posted 30 Sep 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 51 references that are in the map. First posted on arXiv 30 Sep 2024.

Builds on

23 of 51 references.

References · 23

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  5. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  6. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  7. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  8. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  9. 2020A Survey on Visual Transformercited by 654
  10. 2021ImageNet-21K Pretraining for the Massescited by 613
  11. 2019Object Detection in 20 Years: A Surveycited by 531
  12. 2021Deep Long-Tailed Learning: A Surveycited by 417
11 more
  1. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  2. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288
  3. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  4. 2021Oriented R-CNN for Object Detectioncited by 231
  5. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  6. 2021CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attentioncited by 139
  7. 2022Slicing Aided Hyper Inference and Fine-tuning for Small Object Detectioncited by 105
  8. 2020Extended Feature Pyramid Network for Small Object Detectioncited by 27
  9. 2019Small Object Detection using Context and Attentioncited by 21
  10. 2023HIC-YOLOv5: Improved YOLOv5 For Small Object Detectioncited by 10
  11. 2022Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Frameworkcited by 5

Built on by

Not cited yet.