重建網絡在無監督異常和分布外 (OOD) 檢測中被廣泛使用，因為它們不依賴於標記的異常數據。然而，在多類別數據集中，重建網絡的泛化能力會削弱異常檢測的效果，導致異常樣本混入由多類別擴展的正常範圍內，從而降低檢測準確性。我們引入了FUTUREG框架，包含兩個創新模組：特徵純化模組 (Feature Purification Module, FPM) 和 CFG 解碼器 (CFG Decoder)。FPM在潛在空間中約束正常範圍，有效過濾掉異常特徵，而CFG解碼器利用分層編碼器表示來引導過濾後特徵的重建，保留細緻的細節。這兩個模組共同提高了異常樣本的重建誤差，並確保正常樣本的高質量重建。我們的結果顯示，FUTUREG在多類別OOD設置中達到了最先進的性能，並在工業異常檢測場景中保持競爭力。

Reconstruction networks are prevalently used in unsupervised anomaly and Out-of-Distribution (OOD) detection due to their independence from labeled anomaly data. However, in multi-class datasets, the effectiveness of anomaly detection is often compromised by the models' generalized reconstruction capabilities, which allow anomalies to blend within the expanded boundaries of normality resulting from the added categories, thereby reducing detection accuracy. We introduce the FUTUREG framework, which incorporates two innovative modules: the Feature Purification Module (FPM) and the CFG Decoder. The FPM constrains the normality boundary within the latent space to effectively filter out anomalous features, while the CFG Decoder uses layer-wise encoder representations to guide the reconstruction of filtered features, preserving fine-grained details. Together, these modules enhance the reconstruction error for anomalies, ensuring high-quality reconstructions for normal samples. Our results demonstrate that FUTUREG achieves state-of-the-art performance in multi-class OOD settings and remains competitive in industrial anomaly detection scenarios.

[1] J. An and S. Cho. Variational autoencoder based anomaly detection using reconstruction probability, 2015.

[2] A. Anandakrishnan, S. Kumar, A. Statnikov, T. Faruquie, and D. Xu. Anomaly detection in finance: Editors' introduction. In KDD 2017 Workshop on Anomaly Detection in Finance, pages 1–7, 2018.

[3] P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger. Mvtec ad–a comprehensive real-world dataset for unsupervised anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9592–9600, 2019.

[4] P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4183–4192, 2020.

[5] L. Chen, Z. You, N. Zhang, J. Xi, and X. Le. Utrad: Anomaly detection and localization with u-transformer, 2022.

[6] T. Defard, A. Setkov, A. Loesch, and R. Audigier. Padim: A patch distribution modeling framework for anomaly detection and localization. In Proceedings of the International Conference on Pattern Recognition, pages 475–489, 2021.

[7] H. Deng and X. Li. Anomaly detection via reverse distillation from one-class embedding. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9737–9746, 2022.

[8] L. Deng. The mnist database of handwritten digit images for machine learning research, 2012.

[9] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, and S. Gelly. An image is worth 16x16 words: Transformers for image recognition at scale, 2020.

[10] M. Evangelou and N. M. Adams. An anomaly detection framework for cyber-security data, 2020.

[11] S. Fan, C. Shi, and X. Wang. Abnormal event detection via heterogeneous information network embedding. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 1483–1486, 2018.

[12] D. Fontanel, F. Cermelli, M. Mancini, and B. Caputo. Detecting anomalies in semantic segmentation with prototypes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 113–121, 2021.

[13] N. Görnitz, M. Kloft, K. Rieck, and U. Brefeld. Toward supervised anomaly detection, 2013.

[14] A. Krizhevsky and G. Hinton. Learning multiple layers of features from tiny images, 2009.

[15] Y. Lee and P. Kang. Anovit: Unsupervised anomaly detection and localization with vision transformer-based encoder-decoder, 2022.

[16] G. Li, V. Jampani, L. Sevilla-Lara, D. Sun, J. Kim, and J. Kim. Adaptive prototype learning and allocation for few-shot segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8334–8343, 2021.

[17] Z. Liu, Y. Zhou, Y. Xu, and Z. Wang. Simplenet: A simple network for image anomaly detection and localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20402–20411, 2023.

[18] R. Lu, Y. Wu, L. Tian, D. Wang, B. Chen, X. Liu, and R. Hu. Hierarchical vector quantized transformer for multi-class unsupervised anomaly detection, 2024.

[19] P. Mishra, R. Verk, D. Fornasier, C. Piciarelli, and G. L. Foresti. Vt-adl: A vision transformer network for image anomaly detection and localization. In 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), pages 01–06, 2021.

[20] T. Reiss, N. Cohen, L. Bergman, and Y. Hoshen. Panda: Adapting pretrained features for anomaly detection and segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2806–2814, 2021.

[21] K. Roth, L. Pemula, J. Zepeda, B. Schölkopf, T. Brox, and P. Gehler. Towards total recall in industrial anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14318–14328, 2022.

[22] E. Šabić, D. Keeley, B. Henderson, and S. Nannemann. Healthcare and anomaly detection: Using machine learning to predict anomalies in heart rate data, 2021.

[23] M. Salehi, N. Sadjadi, S. Baselizadeh, M. H. Rohban, and H. R. Rabiee. Multiresolution knowledge distillation for anomaly detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14902–14912, 2021.

[24] T. Schlegl, P. Seeböck, S. M. Waldstein, G. Langs, and U. Schmidt-Erfurth. f-anogan: Fast unsupervised anomaly detection with generative adversarial networks, 2019.

[25] J. Snell, K. Swersky, and R. Zemel. Prototypical networks for few-shot learning, 2017.

[26] M. Tan and Q. Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning, pages 6105–6114, 2019.

[27] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. Gomez, L. Kaiser, and I. Polosukhin. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30, 2017.

[28] K. Wang, J. H. Liew, Y. Zou, D. Zhou, and J. Feng. Panet: Few-shot image semantic segmentation with prototype alignment. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9197–9206, 2019.

[29] J. Xie, R. Girshick, and A. Farhadi. Unsupervised deep embedding for clustering analysis. In Proceedings of the International Conference on Machine Learning, pages 478–487, 2016.

[30] J. Yi and S. Yoon. Patch svdd: Patch-level svdd for anomaly detection and segmentation. In Proceedings of the Asian Conference on Computer Vision, 2020.

[31] Z. You, L. Cui, Y. Shen, K. Yang, X. Lu, Y. Zheng, and X. Le. A unified model for multi-class anomaly detection, 2022.

[32] V. Zavrtanik, M. Kristan, and D. Skočaj. Draem: A discriminatively trained reconstruction embedding for surface anomaly detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8330–8339, 2021.