합성 이미지로 이상 탐지 최적화
📝 원문 정보
- Title: Anomaly Detection by Effectively Leveraging Synthetic Images- ArXiv ID: 2512.23227
- 발행일: 2025-12-29
- 저자: Sungho Kang, Hyunkyu Park, Yeonho Lee, Hanbyul Lee, Mijoo Jeong, YeongHyeon Park, Injae Lee, Juneho Yi
📝 초록
Anomaly detection plays a vital role in industrial manufacturing. Due to the scarcity of real defect images, unsupervised approaches that rely solely on normal images have been extensively studied. Recently, diffusion-based generative models brought attention to training data synthesis as an alternative solution. In this work, we focus on a strategy to effectively leverage synthetic images to maximize the anomaly detection performance. Previous synthesis strategies are broadly categorized into two groups, presenting a clear trade-off. Rule-based synthesis, such as injecting noise or pasting patches, is cost-effective but often fails to produce realistic defect images. On the other hand, generative model-based synthesis can create high-quality defect images but requires substantial cost. To address this problem, we propose a novel framework that leverages a pre-trained text-guided image-to-image translation model and image retrieval model to efficiently generate synthetic defect images. Specifically, the image retrieval model assesses the similarity of the generated images to real normal images and filters out irrelevant outputs, thereby enhancing the quality and relevance of the generated defect images. To effectively leverage synthetic images, we also introduce a two stage training strategy. In this strategy, the model is first pre-trained on a large volume of images from rule-based synthesis and then fine-tuned on a smaller set of high-quality images. This method significantly reduces the cost for data collection while improving the anomaly detection performance. Experiments on the MVTec AD dataset demonstrate the effectiveness of our approach.💡 논문 해설
1. 첫 번째 기여: 이 연구는 [주요 발견 또는 방법]을 제시합니다. 이를 이해하는 데 도움이 되는 메타포는 [메타포를 사용하여 개념 설명]. 2. 두 번째 기여: [두 번째 주요 발견 또는 방법]. 이는 마치 [메타포를 사용하여 개념 설명]과 같습니다. 3. 세 번째 기여: [세 번째 주요 발견 또는 방법]. 이는 [메타포를 사용하여 개념 설명]을 이해하는 데 도움이 됩니다.[Sci-Tube 스타일의 간단한 설명] 초보자: [원문 내용에 대한 가장 단순화된 설명] 중급자: [그 다음으로 복잡한 수준에서 원문 내용에 대한 설명] 고급자: [원문 내용에 대해 가장 상세하고 기술적인 설명]
📄 논문 발췌 (ArXiv Source)
📊 논문 시각자료 (Figures)
