Saved in:
Bibliographic Details
Main Authors: Zhang, Hao, Zhang, Shuaijie, Zou, Renbin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.05412
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917688548261888
author Zhang, Hao
Zhang, Shuaijie
Zou, Renbin
author_facet Zhang, Hao
Zhang, Shuaijie
Zou, Renbin
contents Data augmentation refers to the process of applying a series of transformations or expansions to original data to generate new samples, thereby increasing the diversity and quantity of the data, effectively improving the performance and robustness of models. As a common data augmentation method, Mosaic data augmentation technique stitches multiple images together to increase the diversity and complexity of training data, thereby reducing the risk of overfitting. Although Mosaic data augmentation achieves excellent results in general detection tasks by stitching images together, it still has certain limitations for specific detection tasks. This paper addresses the challenge of detecting a large number of densely distributed small objects in aerial images by proposing the Select-Mosaic data augmentation method, which is improved with a fine-grained region selection strategy. The improved Select-Mosaic method demonstrates superior performance in handling dense small object detection tasks, significantly enhancing the accuracy and stability of detection models. Code is available at https://github.com/malagoutou/Select-Mosaic.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05412
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes
Zhang, Hao
Zhang, Shuaijie
Zou, Renbin
Computer Vision and Pattern Recognition
Data augmentation refers to the process of applying a series of transformations or expansions to original data to generate new samples, thereby increasing the diversity and quantity of the data, effectively improving the performance and robustness of models. As a common data augmentation method, Mosaic data augmentation technique stitches multiple images together to increase the diversity and complexity of training data, thereby reducing the risk of overfitting. Although Mosaic data augmentation achieves excellent results in general detection tasks by stitching images together, it still has certain limitations for specific detection tasks. This paper addresses the challenge of detecting a large number of densely distributed small objects in aerial images by proposing the Select-Mosaic data augmentation method, which is improved with a fine-grained region selection strategy. The improved Select-Mosaic method demonstrates superior performance in handling dense small object detection tasks, significantly enhancing the accuracy and stability of detection models. Code is available at https://github.com/malagoutou/Select-Mosaic.
title Select-Mosaic: Data Augmentation Method for Dense Small Object Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.05412