# GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection

arXiv: https://arxiv.org/abs/2406.07487 · HTML: https://mlsanity.com/paper/2406.07487/

## Key facts

- Cited by 42 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 31 of its 36 references that are in the map.
- First posted on arXiv 11 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, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [ControlVideo: Training-free Controllable Text-to-Video Generation](https://mlsanity.com/paper/2305.13077/) (2023)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders](https://mlsanity.com/paper/1807.02011/) (2018)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection](https://mlsanity.com/paper/2403.12580/) (2024)
- [APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD](https://mlsanity.com/paper/2305.17382/) (2023)
- [Asymmetric Student-Teacher Networks for Industrial Anomaly Detection](https://mlsanity.com/paper/2210.07829/) (2022)
- [Towards Visually Explaining Variational Autoencoders](https://mlsanity.com/paper/1911.07389/) (2019)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities](https://mlsanity.com/paper/2205.00908/) (2022)
- [Anomaly Detection with Conditioned Denoising Diffusion Models](https://mlsanity.com/paper/2305.15956/) (2023)
- [DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection](https://mlsanity.com/paper/2312.06607/) (2023)
- [VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON](https://mlsanity.com/paper/2306.07890/) (2023)
- [SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions](https://mlsanity.com/paper/2404.06451/) (2024)

## Built on by (most cited first, 30 of 42)

- [Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2502.07601/) (2025)
- [One-for-More: Continual Diffusion Model for Anomaly Detection](https://mlsanity.com/paper/2502.19848/) (2025)
- [Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2503.19357/) (2025)
- [Triad: Empowering LMM-based Anomaly Detection with Vision Expert-guided Visual Tokenizer and Manufacturing Process](https://mlsanity.com/paper/2503.13184/) (2025)
- [PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies](https://mlsanity.com/paper/2506.09237/) (2025)
- [Anomaly Detection and Generation with Diffusion Models: A Survey](https://mlsanity.com/paper/2506.09368/) (2025)
- [Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning](https://mlsanity.com/paper/2508.02293/) (2025)
- [A Survey on Industrial Anomaly Synthesis](https://mlsanity.com/paper/2502.16412/) (2025)
- [Kaputt: A Large-Scale Dataset for Visual Defect Detection](https://mlsanity.com/paper/2510.05903/) (2025)
- [A Survey on Foundation-Model-Based Industrial Defect Detection](https://mlsanity.com/paper/2502.19106/) (2025)
- [ONER: Online Experience Replay for Incremental Anomaly Detection](https://mlsanity.com/paper/2412.03907/) (2024)
- [InvAD: Inversion-based Reconstruction-Free Anomaly Detection with Diffusion Models](https://mlsanity.com/paper/2504.05662/) (2025)
- [Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2504.11055/) (2025)
- [VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion](https://mlsanity.com/paper/2511.08173/) (2025)
- [A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection](https://mlsanity.com/paper/2603.25159/) (2026)
- [Decompose to Understand, Fuse to Detect: Frequency-Decoupled Anomaly Detection for Encrypted Network Traffic](https://mlsanity.com/paper/2605.02970/) (2026)
- [KairosAD: A SAM-Based Model for Industrial Anomaly Detection on Embedded Devices](https://mlsanity.com/paper/2505.24334/) (2025)
- [Quality-Aware Language-Conditioned Local Auto-Regressive Anomaly Synthesis and Detection](https://mlsanity.com/paper/2508.03539/) (2025)
- [RAID: Retrieval-Augmented Anomaly Detection](https://mlsanity.com/paper/2602.19611/) (2026)
- [Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detection](https://mlsanity.com/paper/2503.23451/) (2025)
- [Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts](https://mlsanity.com/paper/2507.16946/) (2025)
- [A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection](https://mlsanity.com/paper/2508.17827/) (2025)
- [UniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspection](https://mlsanity.com/paper/2601.19222/) (2026)
- [Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks](https://mlsanity.com/paper/2606.02042/) (2026)
- [Attention-Guided Perturbation Network for Industrial Anomaly Detection](https://mlsanity.com/paper/2408.07490/) (2024)
- [Learning local and global prototypes with optimal transport for unsupervised anomaly detection and localization](https://mlsanity.com/paper/2508.12927/) (2025)
- [TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank](https://mlsanity.com/paper/2508.21795/) (2025)
- [Unsupervised Integrated-Circuit Defect Segmentation via Image-Intrinsic Normality](https://mlsanity.com/paper/2509.09375/) (2025)
- [Double Helix Diffusion for Cross-Domain Anomaly Image Generation](https://mlsanity.com/paper/2509.12787/) (2025)
- [Tailored Transformation Invariance for Industrial Anomaly Detection](https://mlsanity.com/paper/2509.17670/) (2025)

## Abstract (arXiv)

Diffusion models have shown superior performance on unsupervised anomaly detection tasks. Since trained with normal data only, diffusion models tend to reconstruct normal counterparts of test images with certain noises added. However, these methods treat all potential anomalies equally, which may cause two main problems. From the global perspective, the difficulty of reconstructing images with different anomalies is uneven. Therefore, instead of utilizing the same setting for all samples, we propose to predict a particular denoising step for each sample by evaluating the difference between image contents and the priors extracted from diffusion models. From the local perspective, reconstructing abnormal regions differs from normal areas even in the same image. Theoretically, the diffusion model predicts a noise for each step, typically following a standard Gaussian distribution. However, due to the difference between the anomaly and its potential normal counterpart, the predicted noise in abnormal regions will inevitably deviate from the standard Gaussian distribution. To this end, we propose introducing synthetic abnormal samples in training to encourage the diffusion models to break through the limitation of standard Gaussian distribution, and a spatial-adaptive feature fusion scheme is utilized during inference. With the above modifications, we propose a global and local adaptive diffusion model (abbreviated to GLAD) for unsupervised anomaly detection, which introduces appealing flexibility and achieves anomaly-free reconstruction while retaining as much normal information as possible. Extensive experiments are conducted on three commonly used anomaly detection datasets (MVTec-AD, MPDD, and VisA) and a printed circuit board dataset (PCB-Bank) we integrated, showing the effectiveness of the proposed method.