mlsanityData to 14 Oct 2026

Aggregated Residual Transformations for Deep Neural Networks

arXiv 1611.05431 ↗First posted 16 Nov 2016cs.CVcited by 2,546

Not on the map. Why?

Cited by 60 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set. This strategy exposes a new dimension, which we call "cardinality" (the size of the set of transformations), as an essential factor in addition to the dimensions of depth and width. On the ImageNet-1K dataset, we empirically show that even under the restricted condition of maintaining complexity, increasing cardinality is able to improve classification accuracy. Moreover, increasing cardinality is more effective than going deeper or wider when we increase the capacity. Our models, named ResNeXt, are the foundations of our entry to the ILSVRC 2016 classification task in which we secured 2nd place. We further investigate ResNeXt on an ImageNet-5K set and the COCO detection set, also showing better results than its ResNet counterpart. The code and models are publicly available online.

Key facts. Cited by 2,546 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 1; 2021: 689; 2022: 591; 2023: 501; 2024: 372; 2025: 276; 2026: 114.

2,546 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2022A ConvNet for the 2020scited by 3,579
  3. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  5. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  6. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  7. 2021ViLT: Vision-and-Language Transformer Without Convolution or Region Supervisioncited by 1,230
  8. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  9. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  10. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  11. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  12. 2021Transformers in Vision: A Surveycited by 1,013
38 more
  1. 2024VMamba: Visual State Space Modelcited by 969
  2. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  3. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  4. 2021Going deeper with Image Transformerscited by 764
  5. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  6. 2021NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actionscited by 744
  7. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 712
  8. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  9. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  10. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  11. 2022Continual Test-Time Domain Adaptationcited by 525
  12. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  13. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  14. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  15. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  16. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  17. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  18. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  19. 2021Deep Long-Tailed Learning: A Surveycited by 417
  20. 2021Early Convolutions Help Transformers See Bettercited by 396
  21. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  22. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  23. 2021MEMO: Test Time Robustness via Adaptation and Augmentationcited by 377
  24. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  25. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  26. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  27. 2021High-Performance Large-Scale Image Recognition Without Normalizationcited by 360
  28. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  29. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
  30. 2021XCiT: Cross-Covariance Image Transformerscited by 338
  31. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  32. 2022How Do Vision Transformers Work?cited by 307
  33. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  34. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 294
  35. 2021ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networkscited by 293
  36. 2021DeepViT: Towards Deeper Vision Transformercited by 289
  37. 2021Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representationcited by 288
  38. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288

50 most cited of 2,546 All 2,546 (JSON)