FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy
This work addresses the need for faster and more accurate mobile or embedded vision models, though it is incremental as it builds upon the MobileNet framework.
The paper tackles the problem of designing efficient neural networks for limited computational budgets by proposing FD-MobileNet, which uses an aggressive downsampling strategy to reduce layers and computational cost while improving performance, achieving a 5.5% top-1 accuracy gain on ILSVRC 2012 and 1.11x inference speedup over MobileNet.
We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying an aggressive downsampling strategy to MobileNet framework. In FD-MobileNet, we perform 32$\times$ downsampling within 12 layers, only half the layers in the original MobileNet. This design brings three advantages: (i) It remarkably reduces the computational cost. (ii) It increases the information capacity and achieves significant performance improvements. (iii) It is engineering-friendly and provides fast actual inference speed. Experiments on ILSVRC 2012 and PASCAL VOC 2007 datasets demonstrate that FD-MobileNet consistently outperforms MobileNet and achieves comparable results with ShuffleNet under different computational budgets, for instance, surpassing MobileNet by 5.5% on the ILSVRC 2012 top-1 accuracy and 3.6% on the VOC 2007 mAP under a complexity of 12 MFLOPs. On an ARM-based device, FD-MobileNet achieves 1.11$\times$ inference speedup over MobileNet and 1.82$\times$ over ShuffleNet under the same complexity.