mlsanityData to 7 Oct 2026

Rethinking the Inception Architecture for Computer Vision

arXiv 1512.00567 ↗First posted 2 Dec 2015cs.CVcited by 5,451

Not on the map. Why?

Cited by 351 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3.5% top-5 error on the validation set (3.6% error on the test set) and 17.3% top-1 error on the validation set.

Key facts. Cited by 5,451 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 3; 2019: 1; 2020: 2; 2021: 1201; 2022: 1137; 2023: 1066; 2024: 866; 2025: 725; 2026: 450.

5,451 papers.

Sort:

By area:

  1. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  2. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  7. 2021ViViT: A Video Vision Transformercited by 1,610
  8. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  9. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  10. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,305
  11. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  12. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
38 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  3. 2021Transformers in Vision: A Surveycited by 1,009
  4. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  5. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 950
  6. 2021Multiscale Vision Transformerscited by 896
  7. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  8. 2021Robust fine-tuning of zero-shot modelscited by 785
  9. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  10. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  11. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  12. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  13. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  14. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  15. 2021Transformer in Transformercited by 632
  16. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  17. 2021ImageNet-21K Pretraining for the Massescited by 607
  18. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  19. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  20. 2021Editing Factual Knowledge in Language Modelscited by 548
  21. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  22. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  23. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  24. 2023VideoMAE V2: Scaling Video Masked Autoencoders with Dual Maskingcited by 516
  25. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  26. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  27. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  28. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  29. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 428
  30. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  31. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  32. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  33. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  34. 2021Early Convolutions Help Transformers See Bettercited by 395
  35. 2023Hyena Hierarchy: Towards Larger Convolutional Language Modelscited by 388
  36. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  37. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  38. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377

50 most cited of 5,451 All 5,451 (JSON)