mlsanityData to 14 Oct 2026

Out of Distribution Performance of State of Art Vision Model

arXiv 2301.10750 ↗First posted 25 Jan 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The vision transformer (ViT) has advanced to the cutting edge in the visual recognition task. Transformers are more robust than CNN, according to the latest research. ViT's self-attention mechanism, according to the claim, makes it more robust than CNN. Even with this, we discover that these conclusions are based on unfair experimental conditions and just comparing a few models, which did not allow us to depict the entire scenario of robustness performance. In this study, we investigate the performance of 58 state-of-the-art computer vision models in a unified training setup based not only on attention and convolution mechanisms but also on neural networks based on a combination of convolution and attention mechanisms, sequence-based model, complementary search, and network-based method. Our research demonstrates that robustness depends on the training setup and model types, and performance varies based on out-of-distribution type. Our research will aid the community in better understanding and benchmarking the robustness of computer vision models.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 76 of its 79 references that are in the map. First posted on arXiv 25 Jan 2023.

Builds on

76 of 79 references.

References · 76

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  8. 2016Densely Connected Convolutional Networkscited by 6,720
  9. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  11. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  12. 2022A ConvNet for the 2020scited by 3,579
38 more
  1. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  2. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  3. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  4. 2019Searching for MobileNetV3cited by 1,994
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  6. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  7. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  8. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  11. 2019Natural Adversarial Examplescited by 1,408
  12. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  13. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  14. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  15. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  16. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,013
  17. 2021Transformers in Vision: A Surveycited by 1,013
  18. 2020Designing Network Design Spacescited by 960
  19. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  20. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  21. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  22. 2021Going deeper with Image Transformerscited by 764
  23. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  24. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  25. 2021Transformer in Transformercited by 633
  26. 2021How to train your ViT? Data, Augmentation, and Regularization in Vision Transformerscited by 569
  27. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  28. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  29. 2017Progressive Neural Architecture Searchcited by 487
  30. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  31. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  32. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  33. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  34. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 470
  35. 2021Intriguing Properties of Vision Transformerscited by 446
  36. 2017Deep Layer Aggregationcited by 436
  37. 2022DeiT III: Revenge of the ViTcited by 419
  38. 2019GhostNet: More Features from Cheap Operationscited by 410

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Exploring Kolmogorov-Arnold Network Expansions in Vision Transformers for Mitigating Catastrophic Forgetting in Continual Learningcited by 1
  2. 2025Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insightscited by 0