A crucial part of image classification consists of capturing non-local spatial semantics of image content. This paper describes the multi-scale hybrid vision transformer (MSHViT), an extension of the classical convolutional neural network (CNN) backbone, for multi-label sewer defect classification. To better model spatial semantics in the images, features are aggregated at different scales non-locally through the use of a lightweight vision transformer, and a smaller set of tokens was produced through a novel Sinkhorn clustering-based tokenizer using distinct cluster centers. The proposed MSHViT and Sinkhorn tokenizer were evaluated on the Sewer-ML multi-label sewer defect classification dataset, showing consistent performance improvements of up to 2.53 percentage points.
Original languageEnglish
Article number104614
JournalAutomation in Construction
Publication statusPublished - Dec 2022


  • Closed-Circuit Television
  • Convolutional Neural Networks
  • Sewer Defect Classification
  • Sewer Inspection
  • Sinkhorn-Knopp
  • Vision Transformers


Dive into the research topics of 'Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification'. Together they form a unique fingerprint.

Cite this