Review for NeurIPS paper: MCUNet: Tiny Deep Learning on IoT Devices

The co-designing mechanism is the core contribution of the paper but the detailed process is not described clearly. It is suggested to provide an elaborate diagram or pseudocode to introduce the whole framework. It is meaningful to explore its generalization ability. Please demonstrate the potential/ability of MCUNet being deployed on more scenarios and tasks, e.g., more devices or tasks like object detection, semantic segmentation. But the experiments failed to highlight the improvements of the co-design scheme, when compared to those single design schemes. But it is unclear whether the overall network topology indeed is the main reason for the huge improvements.