mlsanityData to 7 Oct 2026

A Study on Inference Latency for Vision Transformers on Mobile Devices

arXiv 2510.25166 ↗First posted 29 Oct 2025cs.CV cs.LG cs.PFcited by 1

Not on the map. Why?

Abstract (arXiv)

Given the significant advances in machine learning techniques on mobile devices, particularly in the domain of computer vision, in this work we quantitatively study the performance characteristics of 190 real-world vision transformers (ViTs) on mobile devices. Through a comparison with 102 real-world convolutional neural networks (CNNs), we provide insights into the factors that influence the latency of ViT architectures on mobile devices. Based on these insights, we develop a dataset including measured latencies of 1000 synthetic ViTs with representative building blocks and state-of-the-art architectures from two machine learning frameworks and six mobile platforms. Using this dataset, we show that inference latency of new ViTs can be predicted with sufficient accuracy for real-world applications.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

21 of 33 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  8. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  9. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  11. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  12. 2022MetaFormer Baselines for Visioncited by 131
9 more
  1. 2020Data Movement Is All You Need: A Case Study on Optimizing Transformerscited by 108
  2. 2014Understanding Random Forests: From Theory to Practicecited by 57
  3. 2022EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Predictioncited by 42
  4. 2021FLAT: An Optimized Dataflow for Mitigating Attention Bottleneckscited by 38
  5. 2021DeepEdgeBench: Benchmarking Deep Neural Networks on Edge Devicescited by 26
  6. 2021Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottleneckscited by 22
  7. 2024SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobilecited by 12
  8. 2022Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reductioncited by 4
  9. 2023Exploring the Performance and Efficiency of Transformer Models for NLP on Mobile Devicescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Partition-Aware Scheduling for Mobile Heterogeneous Inference Co-Executioncited by 0