Multi-Task U-Net with Class-Conditional Mahalanobis Scoring for Unsupervised Drone Anomaly Detection
Authors:
- Jeongin JuJJJeongin Ju
- Jungyu ChoiJCJungyu Choi
- Seowoo KimSKSeowoo Kim
- Sungbin ImSISungbin Im
Preprint
- 3 February 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
With the growing use of drones, the importance of early detection of abnormal conditions has increased. However, in real-world scenarios, it is difficult to collect sufficient abnormal data in advance, making unsupervised anomaly detection approaches essential. Conventional autoencoder (AE)-based methods typically use reconstruction error as the anomaly score, but their detection performance degrades when abnormal samples are reconstructed as normal. To address this limitation, this paper proposes a multi-task U-Net that simultaneously performs reconstruction and classification. By applying structured loss functions—Supervised Contrastive (SupCon), Triplet, and Center losses—the proposed model shapes the latent representation into class-conditional Gaussian distributions and computes anomaly scores based on the Mahalanobis distance. Furthermore, the integration of Squeeze-and-Excitation (SE) blocks and an adaptive noise layer enables robust representation learning even under low signal-to-noise ratio (SNR) conditions. Experimental results on the ICSV31-AI Challenge drone acoustic dataset demonstrate that the proposed model achieved a macro Area Under the Curve (AUC) of 0.9630, representing over a 59\% relative improvement compared to the baseline WaveNet AE (0.6059) and significantly outperforming the single-task U-Net (0.5620). These results confirm that the proposed method enables precise, class-aware anomaly detection under unsupervised settings and holds strong potential for applications beyond drones, including various types of industrial equipment.Keywords
This publication has 9 references indexed in Scilit:
- Industrial anomaly detection with domain shift: A real-world dataset and masked multi-scale reconstructionComputers in Industry, 2023
- Deep autoencoders for acoustic anomaly detection: experiments with working machine and in-vehicle audioNeural Computing and Applications, 2022
- Beyond Dents and Scratches: Logical Constraints in Unsupervised Anomaly Detection and LocalizationInternational Journal of Computer Vision, 2022
- Acoustic Anomaly Detection Using Convolutional Autoencoders in Industrial Processes2019
- Deep learning and its applications to machine health monitoringMechanical Systems and Signal Processing, 2019
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987
- A Cluster Separation MeasureIEEE Transactions on Pattern Analysis and Machine Intelligence, 1979
- Index for rating diagnostic testsCancer, 1950