Noisy-ArcMix: Additive Noisy Angular Margin Loss Combined With Mixup Anomalous Sound Detection (2310.06364v1)
Abstract: Unsupervised anomalous sound detection (ASD) aims to identify anomalous sounds by learning the features of normal operational sounds and sensing their deviations. Recent approaches have focused on the self-supervised task utilizing the classification of normal data, and advanced models have shown that securing representation space for anomalous data is important through representation learning yielding compact intra-class and well-separated intra-class distributions. However, we show that conventional approaches often fail to ensure sufficient intra-class compactness and exhibit angular disparity between samples and their corresponding centers. In this paper, we propose a training technique aimed at ensuring intra-class compactness and increasing the angle gap between normal and abnormal samples. Furthermore, we present an architecture that extracts features for important temporal regions, enabling the model to learn which time frames should be emphasized or suppressed. Experimental results demonstrate that the proposed method achieves the best performance giving 0.90%, 0.83%, and 2.16% improvement in terms of AUC, pAUC, and mAUC, respectively, compared to the state-of-the-art method on DCASE 2020 Challenge Task2 dataset.
- “ToyADMOS: A dataset of miniature-machine operating sounds for anomalous sound detection,” in Proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), November 2019, pp. 308–312.
- “Anomalous sound detection based on interpolation deep neural network,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2020, IEEE, pp. 271–275.
- “Self-supervised classification for detecting anomalous sounds,” in Proceedings of Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE), 2020, pp. 46–50.
- “Flow-based self-supervised density estimation for anomalous sound detection,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada, 2021, IEEE, pp. 336–340.
- K. Dohi et al., “Description and discussion on DCASE 2022 challenge task 2: Unsupervised anomalous sound detection for machine condition monitoring applying domain generalization techniques,” in Proceedings of Detection and Classification of Acoustic Scenes and Events 2022 Workshop (DCASE2022), Nancy, France, 2022, pp. 1–5.
- “Anomalous sound detection using spectral-temporal information fusion,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 2022, IEEE, pp. 816–820.
- “Anomalous sound detection using audio representation with machine id based contrastive learning pretraining,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, IEEE, pp. 1–5.
- “Arcface: Additive angular margin loss for deep face recognition,” in Proceedings of IEEE/CVF conference on computer vision and pattern recognition (CVPR), Long Beach, CA, USA, 2019, pp. 4690–4699.
- “mixup: Beyond empirical risk minimization,” in Proceedings of International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 2018.
- K. Wilkinghoff, “Sub-cluster adacos: Learning representations for anomalous sound detection,” in Proceedings of International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, 2021, IEEE, pp. 1–8.
- “Cbam: Convolutional block attention module,” in Proceedings of European conference on computer vision (ECCV), Munich, Germany, 2018, pp. 3–19.
- Y. Koizumi et al., “Description and discussion on DCASE2020 challenge task2: Unsupervised anomalous sound detection for machine condition monitoring,” in Proceedings of Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020), November 2020, pp. 81–85.
- “Vicinal risk minimization,” in Proceedings of the 13th International Conference on Neural Information Processing Systems (NIPS), Denver, CO, USA, 2000, pp. 395–401.
- “Mobilefacenets: Efficient cnns for accurate real-time face verification on mobile devices,” in Biometric Recognition: Chinese Conference, CCBR 2018, Urumqi, China. Springer, 2018, pp. 428–438.
- H. Purohit et al., “MIMII Dataset: Sound dataset for malfunctioning industrial machine investigation and inspection,” in Proceedings of Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), November 2019, pp. 209–213.
- I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in Proceedings of International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, 2018.