# Bayesian Prompt Flow Learning for Zero-Shot Anomaly Detection

arXiv: https://arxiv.org/abs/2503.10080 · HTML: https://mlsanity.com/paper/2503.10080/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 51 references that are in the map.
- First posted on arXiv 13 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 30 of 32)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Visual-Language Prompt Tuning with Knowledge-guided Context Optimization](https://mlsanity.com/paper/2303.13283/) (2023)
- [Multiresolution Knowledge Distillation for Anomaly Detection](https://mlsanity.com/paper/2011.11108/) (2020)
- [AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2310.18961/) (2023)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [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)
- [AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2407.15795/) (2024)
- [CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention](https://mlsanity.com/paper/2209.14169/) (2022)
- [Mixed supervision for surface-defect detection: from weakly to fully supervised learning](https://mlsanity.com/paper/2104.06064/) (2021)
- [Medical Image Analysis using Convolutional Neural Networks: A Review](https://mlsanity.com/paper/1709.02250/) (2017)
- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2311.00453/) (2023)
- [Texts as Images in Prompt Tuning for Multi-Label Image Recognition](https://mlsanity.com/paper/2211.12739/) (2022)
- [FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization](https://mlsanity.com/paper/2404.13671/) (2024)
- [VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation](https://mlsanity.com/paper/2407.12276/) (2024)

## Built on by (most cited first, 30 of 31)

- [VisualAD: Language-Free Zero-Shot Anomaly Detection via Vision Transformer](https://mlsanity.com/paper/2603.07952/) (2026)
- [DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup](https://mlsanity.com/paper/2508.13560/) (2025)
- [MRAD: Zero-Shot Anomaly Detection with Memory-Driven Retrieval](https://mlsanity.com/paper/2602.00522/) (2026)
- [One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection](https://mlsanity.com/paper/2601.05552/) (2026)
- [AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors](https://mlsanity.com/paper/2601.20524/) (2026)
- [GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning](https://mlsanity.com/paper/2602.19206/) (2026)
- [A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects](https://mlsanity.com/paper/2507.13378/) (2025)
- [From Benchmarks to Reality: Advancing Visual Anomaly Detection by the VAND 3.0 Challenge](https://mlsanity.com/paper/2509.17615/) (2025)
- [PromptMoE: Generalizable Zero-Shot Anomaly Detection via Visually-Guided Prompt Mixtures](https://mlsanity.com/paper/2511.18116/) (2025)
- [Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection](https://mlsanity.com/paper/2603.21511/) (2026)
- [CoPS: Conditional Prompt Synthesis for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2508.03447/) (2025)
- [A Contrastive Learning-Guided Confident Meta-learning for Zero Shot Anomaly Detection](https://mlsanity.com/paper/2508.17827/) (2025)
- [Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion](https://mlsanity.com/paper/2601.08022/) (2026)
- [M3-AD: Reflection-aware Multi-modal, Multi-category, and Multi-dimensional Benchmark and Framework for Industrial Anomaly Detection](https://mlsanity.com/paper/2603.00055/) (2026)
- [AG-VAS: Anchor-Guided Zero-Shot Visual Anomaly Segmentation with Large Multimodal Models](https://mlsanity.com/paper/2603.01305/) (2026)
- [FB-CLIP: Fine-Grained Zero-Shot Anomaly Detection with Foreground-Background Disentanglement](https://mlsanity.com/paper/2603.19608/) (2026)
- [A Single Image Is All You Need: Zero-Shot Anomaly Localization Without Training Data](https://mlsanity.com/paper/2509.18354/) (2025)
- [TokenCLIP: Token-wise Prompt Learning for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2510.21171/) (2025)
- [ReBaPL: Repulsive Bayesian Prompt Learning](https://mlsanity.com/paper/2511.17339/) (2025)
- [AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection](https://mlsanity.com/paper/2511.22595/) (2025)
- [SSVP: Synergistic Semantic-Visual Prompting for Industrial Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2601.09147/) (2026)
- [MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection](https://mlsanity.com/paper/2603.03101/) (2026)
- [Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection](https://mlsanity.com/paper/2605.05850/) (2026)
- [Anomaly-Aware Vision-Language Adapters for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2605.12069/) (2026)
- [Res2CLIP: Few-Shot Generalist Anomaly Detection with Residual-to-Residual Alignment](https://mlsanity.com/paper/2605.16171/) (2026)
- [Towards Active Real-to-Twin Inspection: A New Paradigm for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2605.25407/) (2026)
- [EdgeZSAD: Practical Zero-Shot Anomaly Detection on Edge Devices](https://mlsanity.com/paper/2606.16119/) (2026)
- [DifferAD-R1: A Difference-Guided IndustrialAnomaly Localization with Multimodal LargeLanguage Models](https://mlsanity.com/paper/2606.16601/) (2026)
- [LiZAD: A Lightweight Zero-Shot Anomaly Detection Framework for Industrial Manufacturing](https://mlsanity.com/paper/2607.01949/) (2026)
- [Dual Anchors, Do It Better: Hierarchical Group Merging for Zero-Shot Anomaly Detection](https://mlsanity.com/paper/2608.11933/) (2026)

## Abstract (arXiv)

Recently, vision-language models (e.g. CLIP) have demonstrated remarkable performance in zero-shot anomaly detection (ZSAD). By leveraging auxiliary data during training, these models can directly perform cross-category anomaly detection on target datasets, such as detecting defects on industrial product surfaces or identifying tumors in organ tissues. Existing approaches typically construct text prompts through either manual design or the optimization of learnable prompt vectors. However, these methods face several challenges: 1) handcrafted prompts require extensive expert knowledge and trial-and-error; 2) single-form learnable prompts struggle to capture complex anomaly semantics; and 3) an unconstrained prompt space limits generalization to unseen categories. To address these issues, we propose Bayesian Prompt Flow Learning (Bayes-PFL), which models the prompt space as a learnable probability distribution from a Bayesian perspective. Specifically, a prompt flow module is designed to learn both image-specific and image-agnostic distributions, which are jointly utilized to regularize the text prompt space and improve the model's generalization on unseen categories. These learned distributions are then sampled to generate diverse text prompts, effectively covering the prompt space. Additionally, a residual cross-model attention (RCA) module is introduced to better align dynamic text embeddings with fine-grained image features. Extensive experiments on 15 industrial and medical datasets demonstrate our method's superior performance. The code is available at https://github.com/xiaozhen228/Bayes-PFL.