# ZSG-IAD: A Multimodal Framework for Zero-Shot Grounded Industrial Anomaly Detection

arXiv: https://arxiv.org/abs/2604.17949 · HTML: https://mlsanity.com/paper/2604.17949/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 40 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation](https://mlsanity.com/paper/2303.14814/) (2023)
- [Recent Advances in Open Set Recognition: A Survey](https://mlsanity.com/paper/1811.08581/) (2018)
- [FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows](https://mlsanity.com/paper/2111.07677/) (2021)
- [The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization](https://mlsanity.com/paper/2112.09045/) (2021)
- [EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies](https://mlsanity.com/paper/2303.14535/) (2023)
- [Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12367/) (2020)
- [Multimodal Industrial Anomaly Detection via Hybrid Fusion](https://mlsanity.com/paper/2303.00601/) (2023)

## Abstract (arXiv)

Deep learning-based industrial anomaly detectors often behave as black boxes, making it hard to justify decisions with physically meaningful defect evidence. We propose ZSG-IAD, a multimodal vision-language framework for zero-shot grounded industrial anomaly detection. Given RGB images, sensor images, and 3D point clouds, ZSG-IAD generates structured anomaly reports and pixel-level anomaly masks. ZSG-IAD introduces a language-guided two-hop grounding module: (1) anomaly-related sentences select evidence-like latent slots distilled from multimodal features, yielding coarse spatial support; (2) selected slots modulate feature maps via channel-spatial gating and a lightweight decoder to produce fine-grained masks. To improve reliability, we further apply Executable-Rule GRPO with verifiable rewards to promote structured outputs, anomaly-region consistency, and reasoning-conclusion coherence. Experiments across multiple industrial anomaly benchmarks show strong zero-shot performance and more transparent, physically grounded explanations than prior methods. We will release code and annotations to support future research on trustworthy industrial anomaly detection systems.