What augmentations are sensitive to hyper-parameters and why?

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Awais, Ch Muhammad, Bekkouch, Imad Eddine Ibrahim
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911733763801088
author Awais, Ch Muhammad
Bekkouch, Imad Eddine Ibrahim
author_facet Awais, Ch Muhammad
Bekkouch, Imad Eddine Ibrahim
contents We apply augmentations to our dataset to enhance the quality of our predictions and make our final models more resilient to noisy data and domain drifts. Yet the question remains, how are these augmentations going to perform with different hyper-parameters? In this study we evaluate the sensitivity of augmentations with regards to the model's hyper parameters along with their consistency and influence by performing a Local Surrogate (LIME) interpretation on the impact of hyper-parameters when different augmentations are applied to a machine learning model. We have utilized Linear regression coefficients for weighing each augmentation. Our research has proved that there are some augmentations which are highly sensitive to hyper-parameters and others which are more resilient and reliable.
format Preprint
id arxiv_https___arxiv_org_abs_2111_03861
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle What augmentations are sensitive to hyper-parameters and why?
Awais, Ch Muhammad
Bekkouch, Imad Eddine Ibrahim
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
We apply augmentations to our dataset to enhance the quality of our predictions and make our final models more resilient to noisy data and domain drifts. Yet the question remains, how are these augmentations going to perform with different hyper-parameters? In this study we evaluate the sensitivity of augmentations with regards to the model's hyper parameters along with their consistency and influence by performing a Local Surrogate (LIME) interpretation on the impact of hyper-parameters when different augmentations are applied to a machine learning model. We have utilized Linear regression coefficients for weighing each augmentation. Our research has proved that there are some augmentations which are highly sensitive to hyper-parameters and others which are more resilient and reliable.
title What augmentations are sensitive to hyper-parameters and why?
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2111.03861