# Diffusion-based Image Generation for In-distribution Data Augmentation in Surface Defect Detection

arXiv: https://arxiv.org/abs/2406.00501 · HTML: https://mlsanity.com/paper/2406.00501/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 12 of its 17 references that are in the map.
- First posted on arXiv 1 Jun 2024.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities](https://mlsanity.com/paper/2205.00908/) (2022)
- [Prototypical Residual Networks for Anomaly Detection and Localization](https://mlsanity.com/paper/2212.02031/) (2022)

## Built on by (most cited first, 9 of 9)

- [Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect Detection](https://mlsanity.com/paper/2407.03961/) (2024)
- [Self-Supervised Iterative Refinement for Anomaly Detection in Industrial Quality Control](https://mlsanity.com/paper/2408.11561/) (2024)
- [KairosAD: A SAM-Based Model for Industrial Anomaly Detection on Embedded Devices](https://mlsanity.com/paper/2505.24334/) (2025)
- [TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detection](https://mlsanity.com/paper/2603.16451/) (2026)
- [Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language Descriptions](https://mlsanity.com/paper/2604.14941/) (2026)
- [MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance Forecasting](https://mlsanity.com/paper/2412.06840/) (2024)
- [ExDD: Explicit Dual Distribution Learning for Surface Defect Detection via Diffusion Synthesis](https://mlsanity.com/paper/2507.15335/) (2025)
- [RoadFusion: Latent Diffusion Model for Pavement Defect Detection](https://mlsanity.com/paper/2507.15346/) (2025)
- [LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing](https://mlsanity.com/paper/2607.01949/) (2026)

## Abstract (arXiv)

In this study, we show that diffusion models can be used in industrial scenarios to improve the data augmentation procedure in the context of surface defect detection. In general, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the latter are consistently fewer than normal samples. For these reasons, state-of-the-art data augmentation procedures add synthetic defect data by superimposing artifacts to normal samples. This leads to out-of-distribution augmented data so that the classification system learns what is not a normal sample but does not know what a defect really is. We show that diffusion models overcome this situation, providing more realistic in-distribution defects so that the model can learn the defect's genuine appearance. We propose a novel approach for data augmentation that mixes out-of-distribution with in-distribution samples, which we call In&Out. The approach can deal with two data augmentation setups: i) when no defects are available (zero-shot data augmentation) and ii) when defects are available, which can be in a small number (few-shot) or a large one (full-shot). We focus the experimental part on the most challenging benchmark in the state-of-the-art, i.e., the Kolektor Surface-Defect Dataset 2, defining the new state-of-the-art classification AP score under weak supervision of .782. The code is available at https://github.com/intelligolabs/in_and_out.