mlsanityData to 13 Oct 2026

VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

arXiv 2201.08625 ↗First posted 21 Jan 2022cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks. To encourage new and creative ideas on incorporating relevant inductive biases to improve the data efficiency of deep learning models, we prohibited the use of pre-trained checkpoints and other transfer learning techniques. The provided baselines are outperformed by a large margin in all five challenges, mainly thanks to extensive data augmentation policies, model ensembling, and data efficient network architectures.

Key facts. Cited by 8 papers in the map (data through 13 Oct 2026). Builds on 62 of its 75 references that are in the map. First posted on arXiv 21 Jan 2022.

Builds on

62 of 75 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,625
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,991
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,426
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,457
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,170
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,027
  9. 2017Squeeze-and-Excitation Networkscited by 4,772
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,417
  11. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,264
  12. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,882
38 more
  1. 2020Exploring Simple Siamese Representation Learningcited by 2,860
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,544
  3. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,285
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,266
  5. 2017The Kinetics Human Action Video Datasetcited by 1,900
  6. 2018SlowFast Networks for Video Recognitioncited by 1,864
  7. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,628
  8. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,614
  9. 2018Group Normalizationcited by 1,518
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  11. 2017Deformable Convolutional Networkscited by 1,486
  12. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,383
  13. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  14. 2017Random Erasing Data Augmentationcited by 1,238
  15. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  16. 2016Deep Networks with Stochastic Depthcited by 977
  17. 2020Designing Network Design Spacescited by 956
  18. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  19. 2021Multiscale Vision Transformerscited by 896
  20. 2018AutoAugment: Learning Augmentation Policies from Datacited by 730
  21. 2020X3D: Expanding Architectures for Efficient Video Recognitioncited by 635
  22. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 578
  23. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  24. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 498
  25. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  26. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 462
  27. 2020ResNeSt: Split-Attention Networkscited by 445
  28. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  29. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  30. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 381
  31. 2018Rethinking ImageNet Pre-trainingcited by 377
  32. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  33. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  34. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 290
  35. 2017Re-ranking Person Re-identification with k-reciprocal Encodingcited by 260
  36. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  37. 2020Temporal Pyramid Network for Action Recognitioncited by 163
  38. 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 3; 2025: 0; 2026: 1.

8 papers.

  1. 2022Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classificationcited by 4
  2. 2023VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 4
  3. 2023No Data Augmentation? Alternative Regularizations for Effective Training on Small Datasetscited by 1
  4. 20222nd Place Solution for ICCV 2021 VIPriors Image Classification Challenge: An Attract-and-Repulse Learning Approachcited by 0
  5. 2024Augment Before Copy-Paste: Data and Memory Efficiency-Oriented Instance Segmentation Framework for Sport-scenescited by 0
  6. 2024MISS: Memory-efficient Instance Segmentation Framework By Visual Inductive Priors Flow Propagationcited by 0
  7. 2024VIPriors 4: Visual Inductive Priors for Data-Efficient Deep Learning Challengescited by 0
  8. 2026Rethinking Handwritten Character Recognitioncited by 0