mlsanityData to 14 Oct 2026

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

arXiv 1905.11946 ↗First posted 28 May 2019cs.LG cs.CV stat.MLcited by 6,442

Not on the map. Why?

Cited by 133 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters. Source code is at https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet.

Key facts. Cited by 6,442 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 1116; 2022: 1169; 2023: 1269; 2024: 1099; 2025: 1014; 2026: 774.

6,442 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  4. 2022A ConvNet for the 2020scited by 3,579
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  8. 2021Grounded Language-Image Pre-trainingcited by 1,156
  9. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  10. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  11. 2022Token Merging: Your ViT But Fastercited by 1,021
  12. 2021Transformers in Vision: A Surveycited by 1,013
38 more
  1. 2021Scaling Vision Transformerscited by 999
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  3. 2024VMamba: Visual State Space Modelcited by 969
  4. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  5. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  6. 2021Multiscale Vision Transformerscited by 897
  7. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  8. 2021DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsificationcited by 864
  9. 2023Vision-Language Models for Vision Tasks: A Surveycited by 839
  10. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 819
  11. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 815
  12. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  13. 2021Robust fine-tuning of zero-shot modelscited by 797
  14. 2021Going deeper with Image Transformerscited by 764
  15. 2022OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Frameworkcited by 745
  16. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  17. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  18. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  19. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  20. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  21. 2021AST: Audio Spectrogram Transformercited by 643
  22. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  23. 2021Transformer in Transformercited by 633
  24. 2021ImageNet-21K Pretraining for the Massescited by 613
  25. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  26. 2021Carbon Emissions and Large Neural Network Trainingcited by 567
  27. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  28. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  29. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 528
  30. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  31. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  32. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  33. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  34. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  35. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  36. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  37. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  38. 2021Scaling Open-Vocabulary Image Segmentation with Image-Level Labelscited by 473

50 most cited of 6,442 All 6,442 (JSON)