Vision Transformer-Based Multi-Level Feature Fusion for Multi-Label Sewer Defect Classification

arXiv:2609.11375v1 Announce Type: new Abstract: Automated classification of sewer defects is essential for infrastructure condition assessment and maintenance decision-making, but existing deep learning methods struggle to balance classification accuracy and computational complexity in large-scale multi-label scenarios. This study develops Sewer-Transformer-ML, a hierarchical vision Transformer with multi-level feature fusion, together with two lightweight architectures, Sewer-MobileNet-ML and Sewer-Mobile-TransNet, for resource-constrained inspection scenarios. On the Sewer-ML test set, Sewer-Transformer-ML-Base achieved an F2_{ext{CIW}} of 65.68% and an F1_{ext{Normal}} of 92.68%, ranking first on the public leaderboard and exceeding the second-ranked method by 7.6 percentage points in F2_{ext{CIW}}. Sewer-MobileNet-ML achieved an F2_{ext{CIW}} of 65.73% with only 17 M parameters, representing an approximately 95% parameter reduction relative to the base model. Under the standard Sewer-Capsule data split, Sewer-Mobile-TransNet achieved 96.43% classification accuracy. When the training set was reduced to 1,177 images, pretraining on Sewer-ML consistently improved model performance. Ablation experiments further showed that direct concatenation was more effective for Transformer features, whereas attention-based fusion better supported multiscale CNN features. These findings provide a computational basis for automated sewer inspection, lightweight model design, and adaptation across civil infrastructure inspection platforms.

Related

• DSVTLA: Deep Swin Vision Transformer-Based Transfer Learning Architecture for Multi-Type Cancer Histopathological Cancer Image Classification
• WoundFormer: Multi-Scale Spatial Feature Fusion for Multi-Class Wound Tissue Segmentation
• Benchmarking Convolutional, Transformer, Hybrid, and Vision Language Models for Multi Disease Retinal Screening

Source: arXiv cs.CV | 2026-09-11