mlsanityData to 7 Oct 2026

MoireDB: Formula-generated Interference-fringe Image Dataset

arXiv 2502.01490 ↗First posted 3 Feb 2025cs.CV cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Image recognition models have struggled to treat recognition robustness to real-world degradations. In this context, data augmentation methods like PixMix improve robustness but rely on generative arts and feature visualizations (FVis), which have copyright, drawing cost, and scalability issues. We propose MoireDB, a formula-generated interference-fringe image dataset for image augmentation enhancing robustness. MoireDB eliminates copyright concerns, reduces dataset assembly costs, and enhances robustness by leveraging illusory patterns. Experiments show that MoireDB augmented images outperforms traditional Fractal arts and FVis-based augmentations, making it a scalable and effective solution for improving model robustness against real-world degradations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

26 of 38 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2016Wide Residual Networkscited by 3,057
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2018Do Better ImageNet Models Transfer Better?cited by 560
  9. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  10. 2016What makes ImageNet good for transfer learning?cited by 192
  11. 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
  12. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
14 more
  1. 2019Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentationcited by 105
  2. 2021Pre-training without Natural Imagescited by 100
  3. 2021Learning to See by Looking at Noisecited by 92
  4. 2021How Well do Feature Visualizations Support Causal Understanding of CNN Activations?cited by 28
  5. 2020An Effective Anti-Aliasing Approach for Residual Networkscited by 23
  6. 2022Pre-training Vision Transformers with Formula-driven Supervised Learningcited by 21
  7. 2023Visual Atoms: Pre-training Vision Transformers with Sinusoidal Wavescited by 20
  8. 2024Scaling Backwards: Minimal Synthetic Pre-training?cited by 14
  9. 2023Pre-training Vision Transformers with Very Limited Synthesized Imagescited by 12
  10. 2023SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learningcited by 8
  11. 2021Initialization Using Perlin Noise for Training Networks with a Limited Amount of Datacited by 7
  12. 2024Primitive Geometry Segment Pre-training for 3D Medical Image Segmentationcited by 6
  13. 2019Visual Illusions Also Deceive Convolutional Neural Networks: Analysis and Implicationscited by 1
  14. 2022Abutting Grating Illusion: Cognitive Challenge to Neural Network Modelscited by 1

Built on by

Not cited yet.