Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟮𝟲 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗠𝗼𝗯𝗶𝗹𝗲-𝗙𝗼𝗿𝗺𝗲𝗿: Bridging MobileNet and Transformer by Microsoft Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in arxiv2021. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eXnmRPYA ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 We present Mobile-Former, a parallel design of MobileNet and Transformer with a two-way bridge in between. This structure leverages the advantage of MobileNet at local processing and transformer at global interaction. And the bridge enables bidirectional fusion of local and global features. 🔸Different with recent works on vision transformer, the transformer in Mobile-Former contains very few tokens (e.g. less than 6 tokens) that are randomly initialized, resulting in low computational cost. 🔸Combining with the proposed light-weight cross attention to model the bridge, Mobile-Former is not only computationally efficient, but also has more representation power, outperforming MobileNetV3 at low FLOP regime from 25M to 500M FLOPs on ImageNet classification. 🔸For instance, it achieves 77.9\% top-1 accuracy at 294M FLOPs, gaining 1.3\% over MobileNetV3 but saving 17\% of computations. When transferring to object detection, Mobile-Former outperforms MobileNetV3 by 8.6 AP. #computervision #artificialintelligence #data