paint-brush
A Data-centric Approach to Class-specific Bias in Image Data Augmentation: Appendices A-Lby@computational
157 reads

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

by Computational Technology for All
Computational Technology for All HackerNoon profile picture

Computational Technology for All

@computational

Computational: We take random inputs, follow complex steps, and hope...

August 31st, 2024
Read on Terminal Reader
Read this story in a terminal
Print this story
Read this story w/o Javascript
Read this story w/o Javascript
tldt arrow

Too Long; Didn't Read

Data augmentation enhances model generalization in computer vision but may introduce biases, impacting class accuracy unevenly.
featured image - A Data-centric Approach to Class-specific Bias in Image Data Augmentation: Appendices A-L
1x
Read by Dr. One voice-avatar

Listen to this story

Computational Technology for All HackerNoon profile picture
Computational Technology for All

Computational Technology for All

@computational

Computational: We take random inputs, follow complex steps, and hope the output makes sense. And then blog about it.

Learn More
LEARN MORE ABOUT @COMPUTATIONAL'S
EXPERTISE AND PLACE ON THE INTERNET.
0-item

STORY’S CREDIBILITY

Academic Research Paper

Academic Research Paper

Part of HackerNoon's growing list of open-source research papers, promoting free access to academic material.

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.

Appendices

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

[32x32, 31x31, 30x30,

29x29, 28x28, 27x27,

26x26, 25x25, 24x24,

22x22, 21x21, 20x20,

19x19, 18x18, 17x17,

16x16, 15x15, 14x14,

13x13, 12x12, 11x11,

10x10, 9x9, 8x8,

6x6,5x5, 4x4, 3x3]

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

image

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

image

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

image

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

image


(a) The results in all figures employ official ResNet50 models from Tensorflow trained from scratch on the CIFAR-100 dataset with random crop data augmentation applied. All results in this figure are averaged over 4 runs. During training, the proportion of the original image obscured by the augmentation varies from 100% to 10%. We observe The vertical dotted lines denote the best test accuracy for every class.

(a) The results in all figures employ official ResNet50 models from Tensorflow trained from scratch on the CIFAR-100 dataset with random crop data augmentation applied. All results in this figure are averaged over 4 runs. During training, the proportion of the original image obscured by the augmentation varies from 100% to 10%. We observe The vertical dotted lines denote the best test accuracy for every class.


image


(a) The results in all figures employ official ResNet50 models from Tensorflow trained from scratch on the CIFAR-100 dataset with random crop and random horizontal flip data augmentations applied. All results in this figure are averaged over 4 runs. During training, the proportion of the original image obscured by the augmentation varies from 100% to 10%. We observe The vertical dotted lines denote the best test accuracy for every class.

(a) The results in all figures employ official ResNet50 models from Tensorflow trained from scratch on the CIFAR-100 dataset with random crop and random horizontal flip data augmentations applied. All results in this figure are averaged over 4 runs. During training, the proportion of the original image obscured by the augmentation varies from 100% to 10%. We observe The vertical dotted lines denote the best test accuracy for every class.

Appendix F: Full collection of best test performances for CIFAR100

Without Random Horizontal Flip:


image


With Random Horizontal Flip


image

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

image

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

image

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

image

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

image

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

image

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

image


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


L O A D I N G
. . . comments & more!

About Author

Computational Technology for All HackerNoon profile picture
Computational Technology for All@computational
Computational: We take random inputs, follow complex steps, and hope the output makes sense. And then blog about it.

TOPICS

THIS ARTICLE WAS FEATURED IN...

Permanent on Arweave
Read on Terminal Reader
Read this story in a terminal
 Terminal
Read this story w/o Javascript
Read this story w/o Javascript
 Lite
X
Coffee-web
Computational
Briefly
X REMOVE AD