FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy

We present Fast-Downsampling <PRE_TAG>MobileNet</POST_TAG> (FD-<PRE_TAG>MobileNet</POST_TAG>), 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-<PRE_TAG>MobileNet</POST_TAG>, we perform 32times 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-<PRE_TAG>MobileNet</POST_TAG> 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-<PRE_TAG>MobileNet</POST_TAG> achieves 1.11times <PRE_TAG>inference speedup</POST_TAG> over MobileNet and 1.82times over ShuffleNet under the same complexity.