论文标题
部分可观测时空混沌系统的无模型预测
MobileOne: An Improved One millisecond Mobile Backbone
论文作者
论文摘要
用于移动设备的有效神经网络骨干通常针对诸如FLOPS或参数计数之类的指标进行优化。但是，这些指标在移动设备上部署时可能与网络的延迟不太相关。因此，我们通过在移动设备上部署多个移动友好网络来对不同指标进行广泛的分析。我们在最近有效的神经网络中识别和分析建筑和优化瓶颈，并提供减轻这些瓶颈的方法。为此，我们设计了一个有效的骨干莫比尼蛋白，其变体在iPhone12上的推理时间低于1 ms，在Imagenet上具有75.9％的TOP-1精度。我们表明，Mobileone在高效体系结构中实现了最先进的性能，同时在Mobile上的速度更快。我们的最佳模型在38倍的速度中，在ImageNet上的性能与移动形式相似。与在类似潜伏期下的EfficityNet相比，我们的模型在ImageNet上获得了2.3％的TOP-1精度。此外，我们表明我们的模型将概括为多个任务 - 图像分类，对象检测和语义分割，与在移动设备上部署时现有有效体系结构相比，延迟和准确性的显着提高。代码和型号可从https://github.com/apple/ml-mobileone获得
Efficient neural network backbones for mobile devices are often optimized for metrics such as FLOPs or parameter count. However, these metrics may not correlate well with latency of the network when deployed on a mobile device. Therefore, we perform extensive analysis of different metrics by deploying several mobile-friendly networks on a mobile device. We identify and analyze architectural and optimization bottlenecks in recent efficient neural networks and provide ways to mitigate these bottlenecks. To this end, we design an efficient backbone MobileOne, with variants achieving an inference time under 1 ms on an iPhone12 with 75.9% top-1 accuracy on ImageNet. We show that MobileOne achieves state-of-the-art performance within the efficient architectures while being many times faster on mobile. Our best model obtains similar performance on ImageNet as MobileFormer while being 38x faster. Our model obtains 2.3% better top-1 accuracy on ImageNet than EfficientNet at similar latency. Furthermore, we show that our model generalizes to multiple tasks - image classification, object detection, and semantic segmentation with significant improvements in latency and accuracy as compared to existing efficient architectures when deployed on a mobile device. Code and models are available at https://github.com/apple/ml-mobileone
