Explaining Siamese Networks in Few-Shot Learning for Audio Data
| Title | Explaining Siamese Networks in Few-Shot Learning for Audio Data |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Fedele, A, Guidotti, R, Pedreschi, D |
| Conference Name | Discovery Science - 25th International Conference, DS 2022, Montpellier, France, October 10-12, 2022, Proceedings |
| Publisher | Springer |
| Abstract | Machine learning models are not able to generalize correctly when queried on samples belonging to class distributions that were never seen during training. This is a critical issue, since real world applications might need to quickly adapt without the necessity of re-training. To overcome these limitations, few-shot learning frameworks have been proposed and their applicability has been studied widely for computer vision tasks. Siamese Networks learn pairs similarity in form of a metric that can be easily extended on new unseen classes. Unfortunately, the downside of such systems is the lack of explainability. We propose a method to explain the outcomes of Siamese Networks in the context of few-shot learning for audio data. This objective is pursued through a local perturbation-based approach that evaluates segments-weighted-average contributions to the final outcome considering the interplay between different areas of the audio spectrogram. Qualitative and quantitative results demonstrate that our method is able to show common intra-class characteristics and erroneous reliance on silent sections. |
| URL | https://doi.org/10.1007/978-3-031-18840-4_36 |
| DOI | 10.1007/978-3-031-18840-4_36 |