# Why do Angular Margin Losses work well for Semi-Supervised Anomalous Sound Detection?

arXiv: https://arxiv.org/abs/2309.15643 · HTML: https://mlsanity.com/paper/2309.15643/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 85 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 30 of 35)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [Generalizing from a Few Examples: A Survey on Few-Shot Learning](https://mlsanity.com/paper/1904.05046/) (2019)
- [Additive Margin Softmax for Face Verification](https://mlsanity.com/paper/1801.05599/) (2018)
- [In defence of metric learning for speaker recognition](https://mlsanity.com/paper/2003.11982/) (2020)
- [AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations](https://mlsanity.com/paper/1905.00292/) (2019)
- [Learning Deep Features for One-Class Classification](https://mlsanity.com/paper/1801.05365/) (2018)
- [Description and Discussion on DCASE2020 Challenge Task2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring](https://mlsanity.com/paper/2006.05822/) (2020)
- [Anomalous sound detection based on interpolation deep neural network](https://mlsanity.com/paper/2005.09234/) (2020)
- [ToyADMOS2: Another dataset of miniature-machine operating sounds for anomalous sound detection under domain shift conditions](https://mlsanity.com/paper/2106.02369/) (2021)
- [MIMII DG: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization Task](https://mlsanity.com/paper/2205.13879/) (2022)
- [Unsupervised Detection of Anomalous Sound based on Deep Learning and the Neyman-Pearson Lemma](https://mlsanity.com/paper/1810.09133/) (2018)
- [Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques](https://mlsanity.com/paper/2206.05876/) (2022)
- [Description and Discussion on DCASE 2023 Challenge Task 2: First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring](https://mlsanity.com/paper/2305.07828/) (2023)
- [Description and Discussion on DCASE 2021 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring under Domain Shifted Conditions](https://mlsanity.com/paper/2106.04492/) (2021)
- [Flow-based Self-supervised Density Estimation for Anomalous Sound Detection](https://mlsanity.com/paper/2103.08801/) (2021)
- [First-shot anomaly sound detection for machine condition monitoring: A domain generalization baseline](https://mlsanity.com/paper/2303.00455/) (2023)
- [Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples](https://mlsanity.com/paper/2011.02949/) (2020)
- [Threshold Independent Evaluation of Sound Event Detection Scores](https://mlsanity.com/paper/2201.13148/) (2022)
- [ID-Conditioned Auto-Encoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2007.05314/) (2020)
- [Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning](https://mlsanity.com/paper/2006.03429/) (2020)
- [Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts](https://mlsanity.com/paper/2111.06539/) (2021)

## Built on by (most cited first, 4 of 4)

- [Self-Supervised Learning for Anomalous Sound Detection](https://mlsanity.com/paper/2312.09578/) (2023)
- [Can We Predict Anomaly Detection Performance from Embedding-Space Geometry?](https://mlsanity.com/paper/2609.26460/) (2026)
- [Improving Anomalous Sound Detection with Attribute-aware Representation from Domain-adaptive Pre-training](https://mlsanity.com/paper/2509.12845/) (2025)
- [Sub-Band Spectral Matching with Localized Score Aggregation for Robust Anomalous Sound Detection](https://mlsanity.com/paper/2603.13749/) (2026)

## Abstract (arXiv)

State-of-the-art anomalous sound detection systems often utilize angular margin losses to learn suitable representations of acoustic data using an auxiliary task, which usually is a supervised or self-supervised classification task. The underlying idea is that, in order to solve this auxiliary task, specific information about normal data needs to be captured in the learned representations and that this information is also sufficient to differentiate between normal and anomalous samples. Especially in noisy conditions, discriminative models based on angular margin losses tend to significantly outperform systems based on generative or one-class models. The goal of this work is to investigate why using angular margin losses with auxiliary tasks works well for detecting anomalous sounds. To this end, it is shown, both theoretically and experimentally, that minimizing angular margin losses also minimizes compactness loss while inherently preventing learning trivial solutions. Furthermore, multiple experiments are conducted to show that using a related classification task as an auxiliary task teaches the model to learn representations suitable for detecting anomalous sounds in noisy conditions. Among these experiments are performance evaluations, visualizing the embedding space with t-SNE and visualizing the input representations with respect to the anomaly score using randomized input sampling for explanation.