{"url":"/method/mobilenet-v4","slug":"mobilenet-v4","name":"MobileNet-V4","full_name":"MobileNet-V4","full_name_withheld":false,"description_markdown":"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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","paper":"/paper/mobilenetv4-universal-models-for-the-mobile","first_author":"Danfeng Qin","n_authors":14,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/mobilenetv4-universal-models-for-the-mobile"},"source":{"url":"https://arxiv.org/abs/2404.10518v2","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Convolutional Neural Networks","url":"/methods/category/convolutional-neural-networks","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/mobilenetv4-universal-models-for-the-mobile","title":"MobileNetV4 -- Universal Models for the Mobile Ecosystem","date":"2024-04-16","arxiv_id":"2404.10518","n_code_links":7,"syntology":{"ran":6,"of":13,"unverified":7,"pointer_only":1}}],"papers_shown":1,"tasks":[{"task":"/task/image-classification","name":"Image Classification","papers":1},{"task":"/task/architecture-search","name":"Neural Architecture Search","papers":1}],"tasks_shown":2,"n_tasks":2,"usage_by_year":[{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/mobilenet-v4"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}