Neural Architecture Search on Acoustic Scene Classification
This work addresses computational efficiency for acoustic scene classification tasks, representing an incremental improvement with specific gains.
The paper tackled the problem of high computational burden in Acoustic Scene Classification (ASC) by proposing a lightweight baseline network and using Neural Architecture Search (NAS) to find more efficient architectures, achieving a 90.3% F1-score on the DCASE2018 task 5 evaluation set and saving 25% of FLOPs compared to the baseline.
Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden. In this work, we propose a lightweight yet high-performing baseline network inspired by MobileNetV2, which replaces square convolutional kernels with unidirectional ones to extract features alternately in temporal and frequency dimensions. Furthermore, we explore a dynamic architecture space built on the basis of the proposed baseline with the recent Neural Architecture Search (NAS) paradigm, which first trains a supernet that incorporates all candidate networks and then applies a well-known evolutionary algorithm NSGA-II to discover more efficient networks with higher accuracy and lower computational cost. Experimental results demonstrate that our searched network is competent in ASC tasks, which achieves 90.3% F1-score on the DCASE2018 task 5 evaluation set, marking a new state-of-the-art performance while saving 25% of FLOPs compared to our baseline network.