We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices. At its core, we introduce 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, we present 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. The integration of UIB, Mobile MQA and the refined NAS recipe results in a new suite of MNv4 models that are mostly Pareto optimal across mobile CPUs, DSPs, GPUs, as well as specialized accelerators like Apple Neural Engine and Google Pixel EdgeTPU - a characteristic not found in any other models tested. Finally, to further boost accuracy, we introduce a novel distillation technique. Enhanced by this technique, our MNv4-Hybrid-Large model delivers 87% ImageNet-1K accuracy, with a Pixel 8 EdgeTPU runtime of just 3.8ms.

翻译：我们提出最新一代MobileNets，即MobileNetV4（MNv4），该模型专为移动设备设计了具有普适高效性的架构。其核心创新在于引入通用倒置瓶颈（UIB）搜索模块，这是一种统一且灵活的结构，融合了倒置瓶颈（IB）、ConvNext、前馈网络（FFN）以及新型扩展深度可分离卷积（ExtraDW）变体。除UIB外，我们还提出了Mobile MQA——专为移动端加速器设计的注意力模块，可实现高达39%的加速效果。同时，一项优化的神经架构搜索（NAS）方案也被引入，显著提升了MNv4的搜索效率。通过整合UIB、Mobile MQA及精炼的NAS方案，我们构建了全新的MNv4模型系列。该系列在移动CPU、DSP、GPU以及苹果神经引擎、谷歌Pixel EdgeTPU等专用加速器上均展现出帕累托最优性能——这一特性在现有其他测试模型中尚属空白。为进一步提升精度，我们提出了一种新型蒸馏技术。经此技术增强后，我们的MNv4-Hybrid-Large模型在ImageNet-1K上达到87%的准确率，同时Pixel 8 EdgeTPU运行时仅需3.8毫秒。