mlsanityData to 14 Oct 2026

AI Benchmark: All About Deep Learning on Smartphones in 2019

arXiv 1910.06663 ↗First posted 15 Oct 2019cs.PF cs.LGcited by 77

Not on the map. Why?

Abstract (arXiv)

The performance of mobile AI accelerators has been evolving rapidly in the past two years, nearly doubling with each new generation of SoCs. The current 4th generation of mobile NPUs is already approaching the results of CUDA-compatible Nvidia graphics cards presented not long ago, which together with the increased capabilities of mobile deep learning frameworks makes it possible to run complex and deep AI models on mobile devices. In this paper, we evaluate the performance and compare the results of all chipsets from Qualcomm, HiSilicon, Samsung, MediaTek and Unisoc that are providing hardware acceleration for AI inference. We also discuss the recent changes in the Android ML pipeline and provide an overview of the deployment of deep learning models on mobile devices. All numerical results provided in this paper can be found and are regularly updated on the official project website: http://ai-benchmark.com.

Key facts. Cited by 77 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 29; 2022: 20; 2023: 11; 2024: 8; 2025: 6; 2026: 3.

77 papers.

Sort:

By area:

  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 263
  2. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  3. 2021FedScale: Benchmarking Model and System Performance of Federated Learning at Scalecited by 136
  4. 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directionscited by 75
  5. 2022Client Selection in Federated Learning: Principles, Challenges, and Opportunitiescited by 62
  6. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  7. 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
  8. 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
  9. 2025Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latencycited by 34
  10. 2021Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devicescited by 30
  11. 2023TimelyFL: Heterogeneity-aware Asynchronous Federated Learning with Adaptive Partial Trainingcited by 27
  12. 2021Smart at what cost? Characterising Mobile Deep Neural Networks in the wildcited by 25
38 more
  1. 2021Anchor-based Plain Net for Mobile Image Super-Resolutioncited by 24
  2. 2021Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Reportcited by 19
  3. 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
  4. 2021It's always personal: Using Early Exits for Efficient On-Device CNN Personalisationcited by 18
  5. 2021DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Devicecited by 18
  6. 2021Multi-Exit Semantic Segmentation Networkscited by 18
  7. 2023Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devicescited by 17
  8. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
  9. 2021Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 15
  10. 2021Layer Pruning on Demand with Intermediate CTCcited by 13
  11. 2022Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Reportcited by 13
  12. 2022MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learningcited by 13
  13. 2024LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognitioncited by 13
  14. 2022Benchmarking of DL Libraries and Models on Mobile Devicescited by 12
  15. 2022FastML Science Benchmarks: Accelerating Real-Time Scientific Edge Machine Learningcited by 12
  16. 2021Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Reportcited by 10
  17. 2023Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoningcited by 10
  18. 2024Understanding Large Language Models in Your Pockets: Performance Study on COTS Mobile Devicescited by 10
  19. 2021Personalized Semi-Supervised Federated Learning for Human Activity Recognitioncited by 9
  20. 2021Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directionscited by 9
  21. 2022Learning Symbolic Model-Agnostic Loss Functions via Meta-Learningcited by 9
  22. 2021One Proxy Device Is Enough for Hardware-Aware Neural Architecture Searchcited by 8
  23. 2022Partial Model Averaging in Federated Learning: Performance Guarantees and Benefitscited by 8
  24. 2021OODIn: An Optimised On-Device Inference Framework for Heterogeneous Mobile Devicescited by 7
  25. 2022TT-NF: Tensor Train Neural Fieldscited by 7
  26. 2022PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networkscited by 7
  27. 2022Fast Nearest Convolution for Real-Time Efficient Image Super-Resolutioncited by 6
  28. 2023Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloadscited by 6
  29. 2023SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Devicecited by 5
  30. 2022FedorAS: Federated Architecture Search under system heterogeneitycited by 4
  31. 2022Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Reportcited by 4
  32. 2023EPAM: A Predictive Energy Model for Mobile AIcited by 4
  33. 2022Sliding Window Recurrent Network for Efficient Video Super-Resolutioncited by 3
  34. 2022Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokehcited by 3
  35. 2022Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Reportcited by 3
  36. 2021How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architecturescited by 2
  37. 2022Adaptive Edge Offloading for Image Classification Under Rate Limitcited by 2
  38. 2022Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Reportcited by 2

50 most cited of 77 All 77 (JSON)