Adaptive Momentum Teacher Reconstruction for Unsupervised Rail Surface Anomaly Detection

Labeled rail surface defect samples are scarce, defect types are diverse, and pixel-level annotations are costly to obtain, which limits the practical applicability of supervised learning methods. To address identity mapping, unstable reconstruction under limited training data, and abrupt gradient changes caused by hard-threshold mining in reconstruction-based unsupervised anomaly detection, we propose Adaptive Momentum Teacher Reconstruction (AMTR). AMTR comprises three complementary modules: the Adaptive Perturbation Bottleneck (APB) dynamically scales perturbations according to feature magnitude and removes the attention-input residual connection in the first decoder block to suppress identity mapping; Feature Discrepancy-Guided Gradient Mining (FDGM) uses continuous position-wise weights to modulate backward gradients; and Momentum Teacher Consistency Learning (MTCL) employs an exponential moving average teacher to provide stable reconstruction targets. On the evaluated RSDDs-AUG split, AMTR achieves the highest mean result for each of the seven metrics among the compared methods. In three independent runs, it achieves mean image-level AUROC and pixel-level AUPRO values of 99.30±0.04% and 77.98±0.51%, respectively. Ablation studies provide evidence for the contributions of the proposed modules. The experimental evaluation is conducted on the RSDDs-AUG dataset, while generalization to other rail datasets and inspection conditions remains to be further investigated.

Authors

Institutions

Publication Details

Journal
Inventions
Published
2026-11-17
DOI
https://doi.org/10.3390/inventions11060126
Primary Topic
Infrastructure Maintenance and Monitoring
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Adaptive Momentum Teacher Reconstruction for Unsupervised Rail Surface Anomaly Detection

Runliang Tian, Zelong You, Dongyu Fan, Ruifeng Ding et al.
4 links
Inventions
Infrastructure Maintenance and Monitoring
article

Adaptive Momentum Teacher Reconstruction for Unsupervised Rail Surface Anomaly Detection

Runliang Tian, Zelong You, Dongyu Fan, Ruifeng Ding, Yixin Song
article en

Abstract

Labeled rail surface defect samples are scarce, defect types are diverse, and pixel-level annotations are costly to obtain, which limits the practical applicability of supervised learning methods. To address identity mapping, unstable reconstruction under limited training data, and abrupt gradient changes caused by hard-threshold mining in reconstruction-based unsupervised anomaly detection, we propose Adaptive Momentum Teacher Reconstruction (AMTR). AMTR comprises three complementary modules: the Adaptive Perturbation Bottleneck (APB) dynamically scales perturbations according to feature magnitude and removes the attention-input residual connection in the first decoder block to suppress identity mapping; Feature Discrepancy-Guided Gradient Mining (FDGM) uses continuous position-wise weights to modulate backward gradients; and Momentum Teacher Consistency Learning (MTCL) employs an exponential moving average teacher to provide stable reconstruction targets. On the evaluated RSDDs-AUG split, AMTR achieves the highest mean result for each of the seven metrics among the compared methods. In three independent runs, it achieves mean image-level AUROC and pixel-level AUPRO values of 99.30±0.04% and 77.98±0.51%, respectively. Ablation studies provide evidence for the contributions of the proposed modules. The experimental evaluation is conducted on the RSDDs-AUG dataset, while generalization to other rail datasets and inspection conditions remains to be further investigated.

InventionsVol. 11(6)
Shijiazhuang Tiedao University (CN)
Infrastructure Maintenance and Monitoring
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon