- 简介我们推出了最新一代MobileNets,称为MobileNetV4(MNv4),为移动设备提供了通用高效的架构设计。在其核心,我们介绍了通用倒置瓶颈(UIB)搜索块,这是一个统一而灵活的结构,将倒置瓶颈(IB)、ConvNext、前馈网络(FFN)和一种新颖的Extra Depthwise(ExtraDW)变体合并在一起。除了UIB,我们还提出了Mobile MQA,这是一个专门为移动加速器量身定制的注意力块,可提供39%的加速。我们还介绍了一种优化的神经架构搜索(NAS)配方,提高了MNv4搜索的有效性。UIB、Mobile MQA和优化后的NAS配方的整合,导致了一系列MNv4模型的推出,这些模型在移动CPU、DSP、GPU以及专用加速器(如Apple Neural Engine和Google Pixel EdgeTPU)上大多数是帕累托最优的,这是其他测试模型所没有的特点。最后,为了进一步提高准确性,我们介绍了一种新颖的蒸馏技术。通过这种技术的增强,我们的MNv4-Hybrid-Large模型在Pixel 8 EdgeTPU运行时仅需3.8ms,提供了87%的ImageNet-1K准确性。
- 图表
- 解决问题MobileNetV4: A Universal Architecture for Mobile Devices
- 关键思路The paper introduces the Universal Inverted Bottleneck (UIB) search block, a unified and flexible structure that merges Inverted Bottleneck (IB), ConvNext, Feed Forward Network (FFN), and a novel Extra Depthwise (ExtraDW) variant. Alongside UIB, Mobile MQA, an attention block tailored for mobile accelerators, delivering a significant 39% speedup. An optimized neural architecture search (NAS) recipe is also introduced which improves MNv4 search effectiveness.
- 其它亮点The new suite of MNv4 models are mostly Pareto optimal across mobile CPUs, DSPs, GPUs, as well as specialized accelerators like Apple Neural Engine and Google Pixel EdgeTPU. The MNv4-Hybrid-Large model delivers 87% ImageNet-1K accuracy, with a Pixel 8 EdgeTPU runtime of just 3.8ms. The paper also introduces a novel distillation technique.
- Some related studies in this field include EfficientNet, MnasNet, and MobileNetV3.
沙发等你来抢
去评论
评论
沙发等你来抢