mlsanityData to 14 Oct 2026

AI Benchmark: Running Deep Neural Networks on Android Smartphones

arXiv 1810.01109 ↗First posted 2 Oct 2018cs.AI cs.CVcited by 75

Not on the map. Why?

Abstract (arXiv)

Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem for them, there is still a group of tasks that can easily challenge even high-end devices, namely running artificial intelligence algorithms. In this paper, we present a study of the current state of deep learning in the Android ecosystem and describe available frameworks, programming models and the limitations of running AI on smartphones. We give an overview of the hardware acceleration resources available on four main mobile chipset platforms: Qualcomm, HiSilicon, MediaTek and Samsung. Additionally, we present the real-world performance results of different mobile SoCs collected with AI Benchmark that are covering all main existing hardware configurations.

Key facts. Cited by 75 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 17; 2022: 26; 2023: 6; 2024: 11; 2025: 7; 2026: 8.

75 papers.

Sort:

By area:

  1. 2024MELTing point: Mobile Evaluation of Language Transformerscited by 36
  2. 2022Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customizationcited by 35
  3. 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
  4. 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
  5. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  6. 2023NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancementcited by 31
  7. 2023DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learningcited by 24
  8. 2021EasyFL: A Low-code Federated Learning Platform For Dummiescited by 20
  9. 2021Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Reportcited by 19
  10. 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
  11. 2021Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Imagecited by 18
  12. 2022Perceptual Image Enhancement for Smartphone Real-Time Applicationscited by 18
38 more
  1. 2023Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devicescited by 17
  2. 2025PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancementcited by 17
  3. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
  4. 2021Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 15
  5. 2022XRBench: An Extended Reality (XR) Machine Learning Benchmark Suite for the Metaversecited by 14
  6. 2022Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Reportcited by 13
  7. 2022MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learningcited by 13
  8. 2022Benchmarking of DL Libraries and Models on Mobile Devicescited by 12
  9. 2025MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devicescited by 12
  10. 2022FIT: A Metric for Model Sensitivitycited by 11
  11. 2021Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Reportcited by 10
  12. 2021Efficient Softmax Approximation for Deep Neural Networks with Attention Mechanismcited by 9
  13. 2024Benchmarking Edge AI Platforms for High-Performance ML Inferencecited by 9
  14. 2022PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networkscited by 7
  15. 2022Cyclical Pruning for Sparse Neural Networkscited by 6
  16. 2022Fast Nearest Convolution for Real-Time Efficient Image Super-Resolutioncited by 6
  17. 2022Fine-Grained Address Segmentation for Attention-Based Variable-Degree Prefetchingcited by 5
  18. 2022Real-Time Under-Display Cameras Image Restoration and HDR on Mobile Devicescited by 5
  19. 2023SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Devicecited by 5
  20. 2021Overparametrization of HyperNetworks at Fixed FLOP-Count Enables Fast Neural Image Enhancementcited by 4
  21. 2022Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Reportcited by 4
  22. 2023Towards Optimal Compression: Joint Pruning and Quantizationcited by 4
  23. 2024Freezing of Gait Detection Using Gramian Angular Fields and Federated Learning from Wearable Sensorscited by 4
  24. 2024Generative AI on the Edge: Architecture and Performance Evaluationcited by 4
  25. 2026LLM Inference at the Edge: Mobile, NPU, and GPU Performance Efficiency Trade-offs Under Sustained Loadcited by 4
  26. 2022Model-based Deep Learning Receiver Design for Rate-Splitting Multiple Accesscited by 3
  27. 2022Sliding Window Recurrent Network for Efficient Video Super-Resolutioncited by 3
  28. 2022Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Reportcited by 3
  29. 2022PriMask: Cascadable and Collusion-Resilient Data Masking for Mobile Cloud Inferencecited by 3
  30. 2025Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edgecited by 3
  31. 2025Learned Lightweight Smartphone ISP with Unpaired Datacited by 3
  32. 2021NNStreamer: Efficient and Agile Development of On-Device AI Systemscited by 2
  33. 2022Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Reportcited by 2
  34. 2024Learnable Sparse Customization in Heterogeneous Edge Computingcited by 2
  35. 2024tuGEMM: Area-Power-Efficient Temporal Unary GEMM Architecture for Low-Precision Edge AIcited by 2
  36. 2021Fast and Accurate Camera Scene Detection on Smartphonescited by 1
  37. 2021Robustness Analysis of Deep Learning Frameworks on Mobile Platformscited by 1
  38. 2022CRISPnet: Color Rendition ISP Netcited by 1

50 most cited of 75 All 75 (JSON)