mlsanityData to 7 Oct 2026

White Paper Assistance: A Step Forward Beyond the Shortcut Learning

arXiv 2106.04178 ↗First posted 8 Jun 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The promising performances of CNNs often overshadow the need to examine whether they are doing in the way we are actually interested. We show through experiments that even over-parameterized models would still solve a dataset by recklessly leveraging spurious correlations, or so-called 'shortcuts'. To combat with this unintended propensity, we borrow the idea of printer test page and propose a novel approach called White Paper Assistance. Our proposed method involves the white paper to detect the extent to which the model has preference for certain characterized patterns and alleviates it by forcing the model to make a random guess on the white paper. We show the consistent accuracy improvements that are manifest in various architectures, datasets and combinations with other techniques. Experiments have also demonstrated the versatility of our approach on fine-grained recognition, imbalanced classification and robustness to corruptions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 52 of its 67 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

52 of 67 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  8. 2017On Calibration of Modern Neural Networkscited by 4,860
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  10. 2017Squeeze-and-Excitation Networkscited by 4,763
  11. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  12. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
38 more
  1. 2016Wide Residual Networkscited by 3,057
  2. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  8. 2019Natural Adversarial Examplescited by 1,401
  9. 2018On the Spectral Bias of Neural Networkscited by 1,321
  10. 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
  11. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  12. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  13. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  14. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  15. 2020Designing Network Design Spacescited by 954
  16. 2018Robustness May Be at Odds with Accuracycited by 873
  17. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  18. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  19. 2018Recognition in Terra Incognitacited by 655
  20. 2020What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimationcited by 492
  21. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  22. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 262
  23. 2019Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNetcited by 260
  24. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  25. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  26. 2019Fast AutoAugmentcited by 243
  27. 2015Learning Multi-Domain Convolutional Neural Networks for Visual Trackingcited by 209
  28. 2019SGD on Neural Networks Learns Functions of Increasing Complexitycited by 203
  29. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 180
  30. 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
  31. 2018Training behavior of deep neural network in frequency domaincited by 174
  32. 2016Deep Pyramidal Residual Networkscited by 163
  33. 2019REPAIR: Removing Representation Bias by Dataset Resamplingcited by 157
  34. 2020Learning explanations that are hard to varycited by 132
  35. 2020What shapes feature representations? Exploring datasets, architectures, and trainingcited by 125
  36. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  37. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  38. 2020Shape-Texture Debiased Neural Network Trainingcited by 76

50 most cited of 52 All 52 (JSON)

Built on by

Not cited yet.