Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yerramilli, Sahiti, Tamarapalli, Jayant Sravan, Kulkarni, Tanmay Girish, Francis, Jonathan, Nyberg, Eric
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2404.02353
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911151635300352
author Yerramilli, Sahiti
Tamarapalli, Jayant Sravan
Kulkarni, Tanmay Girish
Francis, Jonathan
Nyberg, Eric
author_facet Yerramilli, Sahiti
Tamarapalli, Jayant Sravan
Kulkarni, Tanmay Girish
Francis, Jonathan
Nyberg, Eric
contents Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning. As a consequence, these models often suffer from overfitting, limiting their ability to generalize to real-world examples. Recent advancements in diffusion models have enabled the generation of photorealistic images based on textual inputs. Leveraging the substantial datasets used to train these diffusion models, we propose a technique to utilize generated images to augment existing datasets. This paper explores various strategies for effective data augmentation to improve the out-of-domain generalization capabilities of deep learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2404_02353
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Semantic Augmentation in Images using Language
Yerramilli, Sahiti
Tamarapalli, Jayant Sravan
Kulkarni, Tanmay Girish
Francis, Jonathan
Nyberg, Eric
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Deep Learning models are incredibly data-hungry and require very large labeled datasets for supervised learning. As a consequence, these models often suffer from overfitting, limiting their ability to generalize to real-world examples. Recent advancements in diffusion models have enabled the generation of photorealistic images based on textual inputs. Leveraging the substantial datasets used to train these diffusion models, we propose a technique to utilize generated images to augment existing datasets. This paper explores various strategies for effective data augmentation to improve the out-of-domain generalization capabilities of deep learning models.
title Semantic Augmentation in Images using Language
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2404.02353