A Data-centric Approach to Class-specific Bias in Image Data Augmentation: Appendices A-L

:::info
Authors:

(1) Athanasios Angelakis, Amsterdam University Medical Center, University of Amsterdam – Data Science Center, Amsterdam Public Health Research Institute, Amsterdam, Netherlands

(2) Andrey Rass, Den Haag, Netherlands.

:::

Table of Links

• Abstract and 1 Introduction
• 2 The Effect Of Data Augmentation-Induced Class-Specific Bias Is Influenced By Data, Regularization and Architecture
• 2.1 Data Augmentation Robustness Scouting
• 2.2 The Specifics Of Data Affect Augmentation-Induced Bias
• 2.3 Adding Random Horizontal Flipping Contributes To Augmentation-Induced Bias
• 2.4 Alternative Architectures Have Variable Effect On Augmentation-Induced Bias
• 3 Conclusion and Limitations, and References
• Appendices A-L

Appendices

Appendix A: Image dimensions (in pixels) off training images after being randomly cropped and before being resized

[32×32, 31×31, 30×30,

29×29, 28×28, 27×27,

26×26, 25×25, 24×24,

22×22, 21×21, 20×20,

19×19, 18×18, 17×17,

16×16, 15×15, 14×14,

13×13, 12×12, 11×11,

10×10, 9×9, 8×8,

6×6,5×5, 4×4, 3×3]

Appendix B: Dataset samples corresponding to the Fashion-MNIST segment used in training

Appendix C: Dataset samples corresponding to the CIFAR-10 segment used in training

Appendix D: Dataset samples corresponding to the CIFAR-100 segment used in training

Appendix E: Full collection of class accuracy plots for CIFAR-100

Appendix F: Full collection of best test performances for CIFAR100

Without Random Horizontal Flip:

With Random Horizontal Flip

Appendix G: Per-class and overall test set performances samples for the Fashion-MNIST + ResNet50 + Random Cropping + Random Horizontal Flip experiment

Appendix H: Per-class and overall test set performances samples for the CIFAR-10 + ResNet50 + Random Cropping + Random Horizontal Flip experiment

Appendix I: Per-class and overall test set performances samples for the Fashion-MNIST + EfficientNetV2S + Random Cropping + Random Horizontal Flip experiment

Appendix J: Per-class and overall test set performances samples for the Fashion-MNIST + ResNet50 + Random Cropping experiment

Appendix K: Per-class and overall test set performances samples for the CIFAR-10 + ResNet50 + Random Cropping experiment

Appendix L: Per-class and overall test set performances samples for the Fashion-MNIST + SWIN Transformer + Random Cropping + Random Horizontal Flip experiment

:::info
This paper is available on arxiv under CC BY 4.0 DEED license.

:::