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 2.3 Adding Random Horizontal Flipping Contributes To Augmentation-Induced Bias As part of this work’s goal was to confirm the effects of DA on the bias-variance trade-off of image classification problems as seen in Balestriero, Bottou, and LeCun (2022), we also chose to delve deeper into the specifics of the DA policy implemented by the original paper. In particular, we felt that it overlooked the possible effects its universal application of Random Horizontal Flipping (henceforth ”RHF”) as a supplemental DA may have introduced. In an effort to investigate this, we once again conducted a series of experiments similar to Section 2.2, this time excluding RHF. Our trials showed (see Figure 3 and appendices F, J and K) similar trends and results when compared to Section 2.1. However, as could be expected from removing a minor source of regularization such as RHF, overall mean performance was marginally worse across all three datasets. In addition, it appears that the thresholds of α (past which overall and class-specific performances begin to fall, as well as at which best perclass and mean accuracies are reached) have generally increased - for example, ”Sandal”’s best performance is up to 40% from 36% compared to the previous section. In this way, we see that RHF compounds with the scaling Random Cropping DA, acting as a ”constant” source of additional regularization, while preserving, if accelerating, the dynamics of test set accuracies as α grows. With this in mind, Balestriero, Bottou, and LeCun (2022) is validated, as the conclusions reached in the work would likely not have been impacted had RHF been omitted. While not gravely consequential, this finding should serve as a reminder that caution should be exercised when chaining a plurality of data augmentations together. While such an approach is standard practice in contemporary computer vision tasks, it can rapidly increase complexity, and controlling for the influence of a given augmentation on class-specific bias may become difficult. This paper is available on arxiv under CC BY 4.0 DEED license. 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. Authors: 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 Abstract and 1 Introduction Abstract and 1 Introduction 2 The Effect Of Data Augmentation-Induced Class-Specific Bias Is Influenced By Data, Regularization and Architecture 2 The Effect Of Data Augmentation-Induced Class-Specific Bias Is Influenced By Data, Regularization and Architecture 2.1 Data Augmentation Robustness Scouting 2.1 Data Augmentation Robustness Scouting 2.2 The Specifics Of Data Affect Augmentation-Induced Bias 2.2 The Specifics Of Data Affect Augmentation-Induced Bias 2.3 Adding Random Horizontal Flipping Contributes To 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 2.4 Alternative Architectures Have Variable Effect On Augmentation-Induced Bias 3 Conclusion and Limitations, and References 3 Conclusion and Limitations, and References Appendices A-L Appendices A-L 2.3 Adding Random Horizontal Flipping Contributes To Augmentation-Induced Bias As part of this work’s goal was to confirm the effects of DA on the bias-variance trade-off of image classification problems as seen in Balestriero, Bottou, and LeCun (2022), we also chose to delve deeper into the specifics of the DA policy implemented by the original paper. In particular, we felt that it overlooked the possible effects its universal application of Random Horizontal Flipping (henceforth ”RHF”) as a supplemental DA may have introduced. In an effort to investigate this, we once again conducted a series of experiments similar to Section 2.2, this time excluding RHF. Our trials showed (see Figure 3 and appendices F, J and K) similar trends and results when compared to Section 2.1. However, as could be expected from removing a minor source of regularization such as RHF, overall mean performance was marginally worse across all three datasets. In addition, it appears that the thresholds of α (past which overall and class-specific performances begin to fall, as well as at which best perclass and mean accuracies are reached) have generally increased - for example, ”Sandal”’s best performance is up to 40% from 36% compared to the previous section. In this way, we see that RHF compounds with the scaling Random Cropping DA, acting as a ”constant” source of additional regularization, while preserving, if accelerating, the dynamics of test set accuracies as α grows. With this in mind, Balestriero, Bottou, and LeCun (2022) is validated, as the conclusions reached in the work would likely not have been impacted had RHF been omitted. While not gravely consequential, this finding should serve as a reminder that caution should be exercised when chaining a plurality of data augmentations together. While such an approach is standard practice in contemporary computer vision tasks, it can rapidly increase complexity, and controlling for the influence of a given augmentation on class-specific bias may become difficult. This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

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

A Data-centric Approach to Class-specific Bias in Image Data Augmentation: Abstract and Intro

Where does In-context Translation Happen in Large Language Models: Further Analysis

Computational.TECH

Too Long; Didn't Read

Make resilience your competitive advantage

Adding Random Horizontal Flipping Contributes To Augmentation-Induced Bias

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

Spatial-Photonic Ising Machines and the Next Era of Computing

A Data-centric Approach to Class-specific Bias in Image Data Augmentation: Abstract and Intro

The Effect Of Data Augmentation-Induced Class-Specific Bias Is Influenced By Data, Regularization

Alternative Architectures Have Variable Effect On Augmentation-Induced Bias

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

Spatial-Photonic Ising Machines and the Next Era of Computing

A Data-centric Approach to Class-specific Bias in Image Data Augmentation: Abstract and Intro

The Effect Of Data Augmentation-Induced Class-Specific Bias Is Influenced By Data, Regularization

Alternative Architectures Have Variable Effect On Augmentation-Induced Bias

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

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps