mlsanityData to 7 Oct 2026

Do ImageNet Classifiers Generalize to ImageNet?

arXiv 1902.10811 ↗First posted 13 Feb 2019cs.CV cs.LG stat.MLcited by 1,507

Not on the map. Why?

Cited by 317 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification models generalize to new data. We evaluate a broad range of models and find accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet. However, accuracy gains on the original test sets translate to larger gains on the new test sets. Our results suggest that the accuracy drops are not caused by adaptivity, but by the models' inability to generalize to slightly "harder" images than those found in the original test sets.

Key facts. Cited by 1,507 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 155; 2022: 225; 2023: 312; 2024: 324; 2025: 279; 2026: 212.

1,507 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  4. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  5. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  6. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  8. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  9. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  10. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  11. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  12. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
38 more
  1. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  2. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,021
  3. 2021Scaling Vision Transformerscited by 993
  4. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  5. 2023EVA-CLIP: Improved Training Techniques for CLIP at Scalecited by 786
  6. 2021Robust fine-tuning of zero-shot modelscited by 785
  7. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 762
  8. 2021Domain Generalization: A Surveycited by 760
  9. 2021Going deeper with Image Transformerscited by 759
  10. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  11. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  12. 2022MaPLe: Multi-modal Prompt Learningcited by 685
  13. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  14. 2021Merging Models with Fisher-Weighted Averagingcited by 613
  15. 2021LiT: Zero-Shot Transfer with Locked-image text Tuningcited by 572
  16. 2021Domain Generalization with MixStylecited by 563
  17. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 562
  18. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  19. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  20. 2022DeiT III: Revenge of the ViTcited by 417
  21. 2021Early Convolutions Help Transformers See Bettercited by 395
  22. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 388
  23. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  24. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  25. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  26. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  27. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  28. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 340
  29. 2022Prompt-aligned Gradient for Prompt Tuningcited by 339
  30. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  31. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  32. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  33. 2023Visual-Language Prompt Tuning with Knowledge-guided Context Optimizationcited by 307
  34. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  35. 2024Long-CLIP: Unlocking the Long-Text Capability of CLIPcited by 298
  36. 2023SemDeDup: Data-efficient learning at web-scale through semantic deduplicationcited by 295
  37. 2021Understanding Dataset Difficulty with V-Usable Informationcited by 288
  38. 2023Self-regulating Prompts: Foundational Model Adaptation without Forgettingcited by 272

50 most cited of 1,507 All 1,507 (JSON)