mlsanityData to 7 Oct 2026

NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications

arXiv 1804.03230 ↗First posted 9 Apr 2018cs.CVcited by 146

Not on the map. Why?

Abstract (arXiv)

This work proposes an algorithm, called NetAdapt, that automatically adapts a pre-trained deep neural network to a mobile platform given a resource budget. While many existing algorithms simplify networks based on the number of MACs or weights, optimizing those indirect metrics may not necessarily reduce the direct metrics, such as latency and energy consumption. To solve this problem, NetAdapt incorporates direct metrics into its adaptation algorithm. These direct metrics are evaluated using empirical measurements, so that detailed knowledge of the platform and toolchain is not required. NetAdapt automatically and progressively simplifies a pre-trained network until the resource budget is met while maximizing the accuracy. Experiment results show that NetAdapt achieves better accuracy versus latency trade-offs on both mobile CPU and mobile GPU, compared with the state-of-the-art automated network simplification algorithms. For image classification on the ImageNet dataset, NetAdapt achieves up to a 1.7× speedup in measured inference latency with equal or higher accuracy on MobileNets (V1&V2).

Key facts. Cited by 146 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 59; 2022: 30; 2023: 21; 2024: 10; 2025: 10; 2026: 16.

146 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
  3. 2023DepGraph: Towards Any Structural Pruningcited by 202
  4. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
  5. 2024MobileNetV4 -- Universal Models for the Mobile Ecosystemcited by 98
  6. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  7. 2021Dynamic Slimmable Networkcited by 83
  8. 2023Full Stack Optimization of Transformer Inference: a Surveycited by 79
  9. 2021Adaptive Inference through Early-Exit Networks: Design, Challenges and Directionscited by 74
  10. 2022Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Spacecited by 66
  11. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  12. 2024Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costscited by 51
38 more
  1. 2021FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusioncited by 49
  2. 2022Online Continual Learning for Embedded Devicescited by 48
  3. 2021Hessian-Aware Pruning and Optimal Neural Implantcited by 43
  4. 2022Structural Pruning via Latency-Saliency Knapsackcited by 40
  5. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  6. 2022CHEX: CHannel EXploration for CNN Model Compressioncited by 36
  7. 2021Single Image Depth Prediction with Wavelet Decompositioncited by 34
  8. 2021A Review on Deep Learning in UAV Remote Sensingcited by 32
  9. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  10. 2021Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learningcited by 30
  11. 2021Auto-Split: A General Framework of Collaborative Edge-Cloud AIcited by 29
  12. 2021GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarizationcited by 29
  13. 2021Carrying out CNN Channel Pruning in a White Boxcited by 22
  14. 2022Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolutioncited by 20
  15. 2023AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environmentscited by 19
  16. 2021Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platformscited by 18
  17. 2021Towards Accurate and Compact Architectures via Neural Architecture Transformercited by 17
  18. 2021An Information Theory-inspired Strategy for Automatic Network Pruningcited by 17
  19. 2023Adaptive Sharpness-Aware Pruning for Robust Sparse Networkscited by 17
  20. 2022Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filterscited by 16
  21. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16
  22. 2022Lite Pose: Efficient Architecture Design for 2D Human Pose Estimationcited by 16
  23. 2021Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generationcited by 14
  24. 2022Lightweight Monocular Depth Estimation through Guided Decodingcited by 14
  25. 2021Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-designcited by 13
  26. 2021NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimizationcited by 13
  27. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  28. 2021Rethinking Co-design of Neural Architectures and Hardware Acceleratorscited by 12
  29. 2021Real-time Monocular Depth Estimation with Sparse Supervision on Mobilecited by 12
  30. 2022Soft Masking for Cost-Constrained Channel Pruningcited by 12
  31. 2021LANA: Latency Aware Network Accelerationcited by 11
  32. 2021Learning Versatile Neural Architectures by Propagating Network Codescited by 9
  33. 2021Searching for Efficient Multi-Stage Vision Transformerscited by 9
  34. 2021Resource-Efficient Deep Learning: A Survey on Model-, Arithmetic-, and Implementation-Level Techniquescited by 9
  35. 2023How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspectivecited by 9
  36. 2023Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantizationcited by 9
  37. 2024Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimallycited by 9
  38. 2021Neural Architecture Search as Program Transformation Explorationcited by 8

50 most cited of 146 All 146 (JSON)