IAD-R1: Reinforcing Consistent Reasoning in Industrial Anomaly Detection

TL;DR

This paper introduces IAD-R1, a universal post-training framework that significantly improves vision-language models' ability to detect industrial anomalies by enhancing perception and reasoning capabilities through a two-stage training process.

Contribution

IAD-R1 is a novel two-stage training framework that enhances VLMs for industrial anomaly detection, combining high-quality reasoning datasets and policy optimization.

Findings

Average accuracy improved by 43.3% on DAGM dataset

0.5B parameter model surpasses GPT-4.1 and Claude-Sonnet-4 in zero-shot detection

Significant performance gains across 7 different VLM architectures

Abstract

Industrial anomaly detection is a critical component of modern manufacturing, yet the scarcity of defective samples restricts traditional detection methods to scenario-specific applications. Although Vision-Language Models (VLMs) demonstrate significant advantages in generalization capabilities, their performance in industrial anomaly detection remains limited. To address this challenge, we propose IAD-R1, a universal post-training framework applicable to VLMs of different architectures and parameter scales, which substantially enhances their anomaly detection capabilities. IAD-R1 employs a two-stage training strategy: the Perception Activation Supervised Fine-Tuning (PA-SFT) stage utilizes a meticulously constructed high-quality Chain-of-Thought dataset (Expert-AD) for training, enhancing anomaly perception capabilities and establishing reasoning-to-answer correlations; the Structured Control Group Relative Policy Optimization (SC-GRPO) stage employs carefully designed reward functions to achieve a capability leap from "Anomaly Perception" to "Anomaly Interpretation". Experimental results demonstrate that IAD-R1 achieves significant improvements across 7 VLMs, the largest improvement was on the DAGM dataset, with average accuracy 43.3% higher than the 0.5B baseline. Notably, the 0.5B parameter model trained with IAD-R1 surpasses commercial models including GPT-4.1 and Claude-Sonnet-4 in zero-shot settings, demonstrating the effectiveness and superiority of IAD-R1. The dataset, code, and all model weights will be publicly available at https://github.com/Yanhui-Lee/IAD-R1.