异常(物理)
异常检测
计算机科学
人工智能
模式识别(心理学)
共形异常
编码器
推论
可控性
光学(聚焦)
物理
公制(单位)
一致性(知识库)
混合异常
相似性(几何)
作者
Yuanyi Duan,Wei Xu,Qinlong Wu,Guo-Sen Xie,Fang Zhao,Caifeng Shan
出处
期刊:
[Association for Computing Machinery]
日期:2025-10-27
卷期号:: 8048-8057
被引量:9
标识
DOI:10.1145/3746027.3755274
摘要
In industrial scenarios, diverse anomalous images are difficult to acquire, significantly limiting the performance of industrial anomaly detection methods. Automatically generating anomalous images for anomaly detection has the potential to solve the above problem. However, existing anomaly generation models are still not satisfactory regarding the authenticity and controllability of anomaly generation. In this paper, we propose a controlled anomaly generation model named AnomalyControl to generate realistic anomalous images aligned highly with both text prompts and anomaly masks. First, we introduce a CLIP-guided anomaly prompt generator that leverages a CLIP text encoder to find anomaly text prompts most aligned with real anomalous images. Secondly, we propose an anomaly appearance and shape decoupling mechanism, which designs an embedding similarity loss to enforce the alignment between the anomaly text prompt and anomalies generated with different shapes at the same location, making the appearance of generated anomalies better maintain semantic consistency when the anomaly shape changes. Then, a training-free local control enhancement strategy is employed to provide stronger control intensity to anomaly regions during inference for finer alignment with anomaly masks. Finally, a hard sample generation module is proposed to create anomalous samples with subtle shapes and imperceptible anomaly appearances, enabling the downstream anomaly detection model to focus on learning low-saliency anomaly features. Extensive experiments demonstrate that anomalous images generated by our model outperform the state-of-the-art anomaly generation methods in terms of authenticity and consistency, and can significantly improve the performance of downstream anomaly detection tasks, especially anomaly localization.
科研通智能强力驱动
Strongly Powered by AbleSci AI