BacalhauNet: A tiny CNN for lightning-fast modulation classification
José M. de la Rosa, Daniel Granhão, Guilherme Carvalho, Tiago Gonçalves, Mónica Figueiredo, Luís Conde Bento, Nuno Paulino, Luís M. Pessoa · ITU Journal on Future and Evolving Technologies · 2022
Deep learning methods have been shown to be competitive solutions for modulation classification tasks, but suffer from being computationally expensive, limiting their use on embedded devices. We propose a new deep neural network architecture which employs known structures, depth-wise separable convolution and residual connections, as well as a compression methodology, which combined lead to a tiny and fast algorithm for modulation classification. Our compressed model won the first place in ITU's AI/ML in 5G Challenge 2021, achieving 61.73× compression over the challenge baseline and being over 2.6× better than the second best submission. The source code of this work is publicly available at github.com/ITU-AI- ML-in-5G-Challenge/ITU-ML5G-PS-007-BacalhauNet.