# SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning

arXiv: https://arxiv.org/abs/2410.14987 · HTML: https://mlsanity.com/paper/2410.14987/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 53 references that are in the map.
- First posted on arXiv 19 Oct 2024.

## Builds on (most cited first, 30 of 40)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection](https://mlsanity.com/paper/2108.07610/) (2021)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [SVDiff: Compact Parameter Space for Diffusion Fine-Tuning](https://mlsanity.com/paper/2303.11305/) (2023)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention](https://mlsanity.com/paper/2305.10431/) (2023)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [A Note on the Inception Score](https://mlsanity.com/paper/1801.01973/) (2018)
- [Few-shot Image Generation via Cross-domain Correspondence](https://mlsanity.com/paper/2104.06820/) (2021)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization](https://mlsanity.com/paper/2109.15222/) (2021)
- [RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection](https://mlsanity.com/paper/2403.05897/) (2024)

## Built on by (most cited first, 27 of 27)

- [A Survey on Industrial Anomaly Synthesis](https://mlsanity.com/paper/2502.16412/) (2025)
- [AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison](https://mlsanity.com/paper/2603.13779/) (2026)
- [TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models](https://mlsanity.com/paper/2601.08011/) (2026)
- [Towards an Incremental Unified Multimodal Anomaly Detection: Augmenting Multimodal Denoising From an Information Bottleneck Perspective](https://mlsanity.com/paper/2603.02629/) (2026)
- [STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment](https://mlsanity.com/paper/2509.06693/) (2025)
- [Real-IAD Variety: Pushing Industrial Anomaly Detection Dataset to a Modern Era](https://mlsanity.com/paper/2511.00540/) (2025)
- [RAID: Retrieval-Augmented Anomaly Detection](https://mlsanity.com/paper/2602.19611/) (2026)
- [One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control](https://mlsanity.com/paper/2603.18093/) (2026)
- [MAGIC: Few-Shot Mask-Guided Anomaly Inpainting with Prompt Perturbation, Spatially Adaptive Guidance, and Context Awareness](https://mlsanity.com/paper/2507.02314/) (2025)
- [Anomaly Detection by Effectively Leveraging Synthetic Images](https://mlsanity.com/paper/2512.23227/) (2025)
- [DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution](https://mlsanity.com/paper/2511.16920/) (2025)
- [DRL-Guided Neural Batch Sampling for Semi-Supervised Pixel-Level Anomaly Detection](https://mlsanity.com/paper/2511.20270/) (2025)
- [AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection](https://mlsanity.com/paper/2511.22595/) (2025)
- [AnomalyAgent: Agentic Industrial Anomaly Synthesis via Tool-Augmented Reinforcement Learning](https://mlsanity.com/paper/2604.07900/) (2026)
- [GroundingAnomaly: Spatially-Grounded Diffusion for Few-Shot Anomaly Synthesis](https://mlsanity.com/paper/2604.08301/) (2026)
- [Large-Scale Universal Defect Generation: Foundation Models and Datasets](https://mlsanity.com/paper/2604.08915/) (2026)
- [CAD 100K: A Comprehensive Multi-Task Dataset for Car Related Visual Anomaly Detection](https://mlsanity.com/paper/2604.09023/) (2026)
- [PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios](https://mlsanity.com/paper/2604.13863/) (2026)
- [Anomaly-Preference Image Generation](https://mlsanity.com/paper/2605.02439/) (2026)
- [CoGeoAD: Hierarchical Color-Geometric Fusion with Multi-View Attention for Zero-Shot 3D Anomaly Detection](https://mlsanity.com/paper/2606.25273/) (2026)
- [OSAGEN: Object-Aware Mask Priors and Multistage Decoupled Diffusion for Industrial Anomaly Generation](https://mlsanity.com/paper/2607.29533/) (2026)
- [Understanding and Overcoming Cross-modal Fusion Bias in Multimodal Anomaly Detection From A Fisher Information Perspective](https://mlsanity.com/paper/2608.00986/) (2026)
- [UniScale: Arbitrary-Scale Industrial Anomaly Generation](https://mlsanity.com/paper/2608.07864/) (2026)
- [DeCo: Zero-Shot Industrial Anomaly Generation through Decoupling and Recoupling](https://mlsanity.com/paper/2608.07904/) (2026)
- [DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation](https://mlsanity.com/paper/2609.02075/) (2026)
- [FLASH: A "Generate Once, Synthesize Many" Framework for Synthetic Anomaly Generation in Industrial Anomaly Detection](https://mlsanity.com/paper/2609.37314/) (2026)
- [CORE: Contrast-and-Reflect for Self-Supervised Prompt Optimization in Anomaly Synthesis](https://mlsanity.com/paper/2610.19610/) (2026)

## Abstract (arXiv)

We introduce SeaS, a unified industrial generative model for automatically creating diverse anomalies, authentic normal products, and precise anomaly masks. While extensive research exists, most efforts either focus on specific tasks, i.e., anomalies or normal products only, or require separate models for each anomaly type. Consequently, prior methods either offer limited generative capability or depend on a vast array of anomaly-specific models. We demonstrate that U-Net's differentiated learning ability captures the distinct visual traits of slightly-varied normal products and diverse anomalies, enabling us to construct a unified model for all tasks. Specifically, we first introduce an Unbalanced Abnormal (UA) Text Prompt, comprising one normal token and multiple anomaly tokens. More importantly, our Decoupled Anomaly Alignment (DA) loss decouples anomaly attributes and binds them to distinct anomaly tokens of UA, enabling SeaS to create unseen anomalies by recombining these attributes. Furthermore, our Normal-image Alignment (NA) loss aligns the normal token to normal patterns, making generated normal products globally consistent and locally varied. Finally, SeaS produces accurate anomaly masks by fusing discriminative U-Net features with high-resolution VAE features. SeaS sets a new benchmark for industrial generation, significantly enhancing downstream applications, with average improvements of +8.66% pixel-level AP for synthesis-based AD approaches, +1.10% image-level AP for unsupervised AD methods, and +12.79% IoU for supervised segmentation models. Code is available at hrefhttps://github.com/HUST-SLOW/SeaShttps://github.com/HUST-SLOW/SeaS.