mlsanityData to 7 Oct 2026

Unproportional mosaicing

arXiv 2303.02081 ↗First posted 3 Mar 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Data shift is a gap between data distribution used for training and data distribution encountered in the real-world. Data augmentations help narrow the gap by generating new data samples, increasing data variability, and data space coverage. We present a new data augmentation: Unproportional mosaicing (Unprop). Our augmentation randomly splits an image into various-sized blocks and swaps its content (pixels) while maintaining block sizes. Our method achieves a lower error rate when combined with other state-of-the-art augmentations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

25 of 33 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016Wide Residual Networkscited by 3,057
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  7. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  8. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  9. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  10. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  11. 2018Albumentations: fast and flexible image augmentationscited by 558
  12. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
13 more
  1. 2019Fast AutoAugmentcited by 243
  2. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  3. 2020SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularizationcited by 149
  4. 2019Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentationcited by 105
  5. 2017Shake-Shake regularizationcited by 87
  6. 2020ResizeMix: Mixing Data with Preserved Object Information and True Labelscited by 68
  7. 2018Data augmentation instead of explicit regularizationcited by 62
  8. 2020SuperMix: Supervising the Mixing Data Augmentationcited by 58
  9. 2018ShakeDrop Regularization for Deep Residual Learningcited by 40
  10. 2020Improving Auto-Augment via Augmentation-Wise Weight Sharingcited by 28
  11. 2019Does Data Augmentation Lead to Positive Margin?cited by 18
  12. 2019A Group-Theoretic Framework for Data Augmentationcited by 14
  13. 2019Learning robust visual representations using data augmentation invariancecited by 5

Built on by

Not cited yet.