# GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detection

arXiv: https://arxiv.org/abs/2504.14919 · HTML: https://mlsanity.com/paper/2504.14919/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 50 references that are in the map.
- First posted on arXiv 21 Apr 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [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)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [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)
- [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)
- [A Unified Model for Multi-class Anomaly Detection](https://mlsanity.com/paper/2206.03687/) (2022)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [Segmentation-Based Deep-Learning Approach for Surface-Defect Detection](https://mlsanity.com/paper/1903.08536/) (2019)
- [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)
- [Towards Visually Explaining Variational Autoencoders](https://mlsanity.com/paper/1911.07389/) (2019)
- [PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection](https://mlsanity.com/paper/2404.05231/) (2024)
- [Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection](https://mlsanity.com/paper/2405.14325/) (2024)
- [Inpainting Transformer for Anomaly Detection](https://mlsanity.com/paper/2104.13897/) (2021)
- [Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2107.13118/) (2021)
- [Consistency-guided Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2306.01195/) (2023)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [Segment Any Anomaly without Training via Hybrid Prompt Regularization](https://mlsanity.com/paper/2305.10724/) (2023)
- [Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models](https://mlsanity.com/paper/2502.07601/) (2025)
- [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, 3 of 3)

- [EMIT: Enhancing MLLMs for Industrial Anomaly Detection via Difficulty-Aware GRPO](https://mlsanity.com/paper/2507.21619/) (2025)
- [Text-Guided Multimodal Unified Industrial Anomaly Detection](https://mlsanity.com/paper/2604.22899/) (2026)
- [TED:Text-Axis Evidence Decomposition for Prompted Anomaly Localization](https://mlsanity.com/paper/2609.39033/) (2026)

## Abstract (arXiv)

Zero-shot anomaly detection (ZSAD) aims to identify anomalies in unseen categories by leveraging CLIP's zero-shot capabilities to match text prompts with visual features. A key challenge in ZSAD is learning general prompts stably and utilizing them effectively, while maintaining both generalizability and category specificity. Although general prompts have been explored in prior works, achieving their stable optimization and effective deployment remains a significant challenge. In this work, we propose GenCLIP, a novel framework that learns and leverages general prompts more effectively through multi-layer prompting and dual-branch inference. Multi-layer prompting integrates category-specific visual cues from different CLIP layers, enriching general prompts with more comprehensive and robust feature representations. By combining general prompts with multi-layer visual features, our method further enhances its generalization capability. To balance specificity and generalization, we introduce a dual-branch inference strategy, where a vision-enhanced branch captures fine-grained category-specific features, while a query-only branch prioritizes generalization. The complementary outputs from both branches improve the stability and reliability of anomaly detection across unseen categories. Additionally, we propose an adaptive text prompt filtering mechanism, which removes irrelevant or atypical class names not encountered during CLIP's training, ensuring that only meaningful textual inputs contribute to the final vision-language alignment.