3CAD：一個大規模真實世界的3C產品數據集，用於無監督異常检測。

3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly

February 9, 2025

作者: Enquan Yang, Peng Xing, Hanyang Sun, Wenbo Guo, Yuanwei Ma, Zechao Li, Dan Zeng

cs.AI

摘要

工業異常檢測在 MVTec-AD 和 VisA 等數據集的支持下取得了進展。然而，這些數據集在缺陷樣本數量、缺陷類型和現實場景可用性方面存在限制。這些限制阻礙了研究人員進一步探索以更高準確性進行工業檢測的性能。為此，我們提出了一個新的大規模異常檢測數據集，名為3CAD，該數據集源自真實的3C生產線。具體而言，所提出的3CAD 包括八種不同類型的製造零件，總計27,039 張高分辨率圖像，標記了像素級異常。3CAD 的主要特點是它涵蓋了不同大小的異常區域、多種異常類型，以及每個異常圖像可能存在多個異常區域和多種異常類型。這是專門用於3C產品質量控制的最大和第一個異常檢測數據集，供社區探索和開發使用。同時，我們提出了一個簡單而有效的無監督異常檢測框架：Coarse-to-Fine 檢測範式與 Recovery Guidance（CFRG）。為了檢測小缺陷異常，所提出的CFRG 使用了粗到細的檢測範式。具體而言，我們利用異質蒸餾模型進行粗定位，然後通過分割模型進行細定位。此外，為了更好地捕捉正常模式，我們引入了恢復特徵作為引導。最後，我們在3CAD 數據集上報告了我們的CFRG 框架和流行的異常檢測方法的結果，展示了強大的競爭力，並提供了一個極具挑戰性的基準，以促進異常檢測領域的發展。數據和代碼可在以下鏈接獲取：https://github.com/EnquanYang2022/3CAD。

English

Industrial anomaly detection achieves progress thanks to datasets such as MVTec-AD and VisA. However, they suf- fer from limitations in terms of the number of defect sam- ples, types of defects, and availability of real-world scenes. These constraints inhibit researchers from further exploring the performance of industrial detection with higher accuracy. To this end, we propose a new large-scale anomaly detection dataset called 3CAD, which is derived from real 3C produc- tion lines. Specifically, the proposed 3CAD includes eight different types of manufactured parts, totaling 27,039 high- resolution images labeled with pixel-level anomalies. The key features of 3CAD are that it covers anomalous regions of different sizes, multiple anomaly types, and the possibility of multiple anomalous regions and multiple anomaly types per anomaly image. This is the largest and first anomaly de- tection dataset dedicated to 3C product quality control for community exploration and development. Meanwhile, we in- troduce a simple yet effective framework for unsupervised anomaly detection: a Coarse-to-Fine detection paradigm with Recovery Guidance (CFRG). To detect small defect anoma- lies, the proposed CFRG utilizes a coarse-to-fine detection paradigm. Specifically, we utilize a heterogeneous distilla- tion model for coarse localization and then fine localiza- tion through a segmentation model. In addition, to better capture normal patterns, we introduce recovery features as guidance. Finally, we report the results of our CFRG frame- work and popular anomaly detection methods on the 3CAD dataset, demonstrating strong competitiveness and providing a highly challenging benchmark to promote the development of the anomaly detection field. Data and code are available: https://github.com/EnquanYang2022/3CAD.