mlsanityData to 14 Oct 2026

Searching for MobileNetV3

arXiv 1905.02244 ↗First posted 6 May 2019cs.CVcited by 1,994

Not on the map. Why?

Cited by 64 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone CPUs through a combination of hardware-aware network architecture search (NAS) complemented by the NetAdapt algorithm and then subsequently improved through novel architecture advances. This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art. Through this process we create two new MobileNet models for release: MobileNetV3-Large and MobileNetV3-Small which are targeted for high and low resource use cases. These models are then adapted and applied to the tasks of object detection and semantic segmentation. For the task of semantic segmentation (or any dense pixel prediction), we propose a new efficient segmentation decoder Lite Reduced Atrous Spatial Pyramid Pooling (LR-ASPP). We achieve new state of the art results for mobile classification, detection and segmentation. MobileNetV3-Large is 3.2% more accurate on ImageNet classification while reducing latency by 15% compared to MobileNetV2. MobileNetV3-Small is 4.6% more accurate while reducing latency by 5% compared to MobileNetV2. MobileNetV3-Large detection is 25% faster at roughly the same accuracy as MobileNetV2 on COCO detection. MobileNetV3-Large LR-ASPP is 30% faster than MobileNetV2 R-ASPP at similar accuracy for Cityscapes segmentation.

Key facts. Cited by 1,994 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 342; 2022: 380; 2023: 374; 2024: 347; 2025: 307; 2026: 244.

1,994 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  2. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  3. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  4. 2021ImageNet-21K Pretraining for the Massescited by 613
  5. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 489
  7. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  8. 2023Universal Guidance for Diffusion Modelscited by 437
  9. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  10. 2023Faster Segment Anything: Towards Lightweight SAM for Mobile Applicationscited by 352
  11. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
  12. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
38 more
  1. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  2. 2021DeepViT: Towards Deeper Vision Transformercited by 289
  3. 2021Distilling Knowledge via Knowledge Reviewcited by 288
  4. 2021Knowledge distillation: A good teacher is patient and consistentcited by 259
  5. 2021I-BERT: Integer-only BERT Quantizationcited by 255
  6. 2021Coordinate Attention for Efficient Mobile Network Designcited by 241
  7. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 241
  8. 2021Mobile-Former: Bridging MobileNet and Transformercited by 235
  9. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 234
  10. 2022DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptationcited by 233
  11. 2021LocalViT: Analyzing Locality in Vision Transformerscited by 228
  12. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  13. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  14. 2023Teaching CLIP to Count to Tencited by 198
  15. 2021AutoFormer: Searching Transformers for Visual Recognitioncited by 188
  16. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 174
  17. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  18. 2022Separable Self-attention for Mobile Vision Transformerscited by 163
  19. 2023Dense Text-to-Image Generation with Attention Modulationcited by 163
  20. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 162
  21. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  22. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  23. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 154
  24. 2022DeepCore: A Comprehensive Library for Coreset Selection in Deep Learningcited by 147
  25. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 144
  26. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 140
  27. 2021Robust High-Resolution Video Matting with Temporal Guidancecited by 137
  28. 2021MoViNets: Mobile Video Networks for Efficient Video Recognitioncited by 135
  29. 2021SEED: Self-supervised Distillation For Visual Representationcited by 134
  30. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 130
  31. 2021Learning High-Speed Flight in the Wildcited by 128
  32. 2022BackdoorBench: A Comprehensive Benchmark of Backdoor Learningcited by 128
  33. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
  34. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  35. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  36. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  37. 2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
  38. 2022Rethinking Vision Transformers for MobileNet Size and Speedcited by 121

50 most cited of 1,994 All 1,994 (JSON)