# Bring the Power of Diffusion Model to Defect Detection

arXiv: https://arxiv.org/abs/2408.13845 · HTML: https://mlsanity.com/paper/2408.13845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 25 Aug 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, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Diffusion models as plug-and-play priors](https://mlsanity.com/paper/2206.09012/) (2022)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model](https://mlsanity.com/paper/2211.00611/) (2022)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [Asymmetric Student-Teacher Networks for Industrial Anomaly Detection](https://mlsanity.com/paper/2210.07829/) (2022)
- [Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training](https://mlsanity.com/paper/2004.06002/) (2020)
- [AutoAssign: Differentiable Label Assignment for Dense Object Detection](https://mlsanity.com/paper/2007.03496/) (2020)
- [PP-YOLOE: An evolved version of YOLO](https://mlsanity.com/paper/2203.16250/) (2022)
- [MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities](https://mlsanity.com/paper/2205.00908/) (2022)
- [DiffusionInst: Diffusion Model for Instance Segmentation](https://mlsanity.com/paper/2212.02773/) (2022)
- [Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning](https://mlsanity.com/paper/2208.03514/) (2022)
- [Search for Better Students to Learn Distilled Knowledge](https://mlsanity.com/paper/2001.11612/) (2020)
- [Reference-based Defect Detection Network](https://mlsanity.com/paper/2108.04456/) (2021)
- [Class-Attentive Diffusion Network for Semi-Supervised Classification](https://mlsanity.com/paper/2006.10222/) (2020)

## Abstract (arXiv)

Due to the high complexity and technical requirements of industrial production processes, surface defects will inevitably appear, which seriously affects the quality of products. Although existing lightweight detection networks are highly efficient, they are susceptible to false or missed detection of non-salient defects due to the lack of semantic information. In contrast, the diffusion model can generate higher-order semantic representations in the denoising process. Therefore, the aim of this paper is to incorporate the higher-order modelling capability of the diffusion model into the detection model, so as to better assist in the classification and localization of difficult targets. First, the denoising diffusion probabilistic model (DDPM) is pre-trained to extract the features of denoising process to construct as a feature repository. In particular, to avoid the potential bottleneck of memory caused by the dataloader loading high-dimensional features, a residual convolutional variational auto-encoder (ResVAE) is designed to further compress the feature repository. The image is fed into both image backbone and feature repository for feature extraction and querying respectively. The queried latent features are reconstructed and filtered to obtain high-dimensional DDPM features. A dynamic cross-fusion method is proposed to fully refine the contextual features of DDPM to optimize the detection model. Finally, we employ knowledge distillation to migrate the higher-order modelling capabilities back into the lightweight baseline model without additional efficiency cost. Experiment results demonstrate that our method achieves competitive results on several industrial datasets.