Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
| Autor: | Koutini, Khaled, Henkel, Florian, Eghbal-zadeh, Hamid, Widmer, Gerhard |
|---|---|
| Rok vydání: | 2020 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | Deep Neural Networks are known to be very demanding in terms of computing and memory requirements. Due to the ever increasing use of embedded systems and mobile devices with a limited resource budget, designing low-complexity models without sacrificing too much of their predictive performance gained great importance. In this work, we investigate and compare several well-known methods to reduce the number of parameters in neural networks. We further put these into the context of a recent study on the effect of the Receptive Field (RF) on a model's performance, and empirically show that we can achieve high-performing low-complexity models by applying specific restrictions on the RFs, in combination with parameter reduction methods. Additionally, we propose a filter-damping technique for regularizing the RF of models, without altering their architecture and changing their parameter counts. We will show that incorporating this technique improves the performance in various low-complexity settings such as pruning and decomposed convolution. Using our proposed filter damping, we achieved the 1st rank at the DCASE-2020 Challenge in the task of Low-Complexity Acoustic Scene Classification. Comment: Proceedings of the Detection and Classification of Acoustic Scenes and Events 2020 Workshop (DCASE2020) |
| Databáze: | arXiv |
| Externí odkaz: |
|