# End-to-end training of a two-stage neural network for defect detection

arXiv: https://arxiv.org/abs/2007.07676 · HTML: https://mlsanity.com/paper/2007.07676/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [A Discrepancy Aware Framework for Robust Anomaly Detection](https://mlsanity.com/paper/2310.07585/) (2023)
- [Self-Supervised Iterative Refinement for Anomaly Detection in Industrial Quality Control](https://mlsanity.com/paper/2408.11561/) (2024)
- [No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes](https://mlsanity.com/paper/2508.19060/) (2025)
- [Explainable fetal ultrasound quality assessment with progressive concept bottleneck models](https://mlsanity.com/paper/2211.10630/) (2022)
- [A Review of Benchmarks for Visual Defect Detection in the Manufacturing Industry](https://mlsanity.com/paper/2305.13261/) (2023)
- [A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it](https://mlsanity.com/paper/2110.05015/) (2021)
- [Decision Fusion Network with Perception Fine-tuning for Defect Classification](https://mlsanity.com/paper/2309.12630/) (2023)
- [Source-Free Test-Time Adaptation For Online Surface-Defect Detection](https://mlsanity.com/paper/2408.09494/) (2024)
- [Change-Aware Siamese Network for Surface Defects Segmentation under Complex Background](https://mlsanity.com/paper/2409.00589/) (2024)

## Abstract (arXiv)

Segmentation-based, two-stage neural network has shown excellent results in the surface defect detection, enabling the network to learn from a relatively small number of samples. In this work, we introduce end-to-end training of the two-stage network together with several extensions to the training process, which reduce the amount of training time and improve the results on the surface defect detection tasks. To enable end-to-end training we carefully balance the contributions of both the segmentation and the classification loss throughout the learning. We adjust the gradient flow from the classification into the segmentation network in order to prevent the unstable features from corrupting the learning. As an additional extension to the learning, we propose frequency-of-use sampling scheme of negative samples to address the issue of over- and under-sampling of images during the training, while we employ the distance transform algorithm on the region-based segmentation masks as weights for positive pixels, giving greater importance to areas with higher probability of presence of defect without requiring a detailed annotation. We demonstrate the performance of the end-to-end training scheme and the proposed extensions on three defect detection datasets - DAGM, KolektorSDD and Severstal Steel defect dataset - where we show state-of-the-art results. On the DAGM and the KolektorSDD we demonstrate 100% detection rate, therefore completely solving the datasets. Additional ablation study performed on all three datasets quantitatively demonstrates the contribution to the overall result improvements for each of the proposed extensions.