A Novel Multi-Sample Data Augmentation Method for Oriented Object Detection in Remote Sensing Images

Chen, Guhua; Pei, Gensheng; Tang, Yin; Chen, Tao; Tang, Zhenmin

doi:10.1109/mmsp55362.2022.9949615

Cited by 4 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly to CV, data augmentation techniques significantly improve the performance and generalization capabilities for RS tasks. Recently, researchers have explored various approaches to tailor well-established CV data augmentation techniques for RS tasks, such as SLC [8], [30], [31], [32], [33], object detection [9], [34], [35], [36], [37], [38], or semantic segmentation tasks [10], [39]. Joined in their purpose to alleviate overfitting and to serve as a form of regularization in small data regimes, the approaches for data augmentation can be broadly divided into three categories: (i) image modification (Section II-A); (ii) image generation (Section II-B); or (iii) image pairing (Section II-C) that also includes CutMix-based approaches.…”

Section: Introductionmentioning

confidence: 99%

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

Burgert

Ravanbakhsh

Demir

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

The development of accurate methods for multilabel classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. To address MLC problems, the use of deep neural networks that require a high number of reliable training images annotated by multiple land-cover class labels (multi-labels) has been found popular in RS. However, collecting such annotations is time-consuming and costly. A common procedure to obtain annotations at zero labeling cost is to rely on thematic products or crowdsourced labels. As a drawback, these procedures come with the risk of label noise that can distort the learning process of the MLC algorithms. In the literature, most label noise robust methods are designed for single-label classification (SLC) problems in computer vision (CV), where each image is annotated by a single label. Unlike SLC, label noise in MLC can be associated with: 1) subtractive label noise (a land cover class label is not assigned to an image while that class is present in the image); 2) additive label noise (a land cover class label is assigned to an image, although that class is not present in the given image); and 3) mixed label noise (a combination of both). In this paper, we investigate three different noise robust CV SLC methods (Self-Adaptive Training, Early-Learning Regularization, and Joint Co-Regularized Training) and adapt them to be robust for multi-label noise scenarios in RS. During experiments, we study the effects of different types of multi-label noise and evaluate the adapted methods rigorously. To this end, we also introduce a synthetic multi-label noise injection strategy that is more adequate to simulate operational scenarios compared to the uniform label noise injection strategy, in which the labels of absent and present classes are flipped at uniform probability. Further, we study the relevance of different evaluation metrics in MLC problems under noisy multi-labels. On the basis of the theoretical and experimental analyses, some guidelines for a proper design of label noise robust MLC methods are derived.

show abstract

Section: Introductionmentioning

confidence: 99%

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

Burgert

Ravanbakhsh

Demir

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

FlexibleCP: A data augmentation strategy for traffic sign detection

Shi,

Rao,

Jing

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

In the field of traffic sign detection, effective data augmentation can improve the model's detection capacity, enabling the model to distinguish and locate traffic signs more precisely and enhancing driving safety. However, due to the small size and low representation of traffic signs in the dataset, standard common data augmentation techniques are not suitable for traffic sign detection. To address this issue, a novel data augmentation strategy called flexible cut and paste (FlexibleCP) is proposed. The overall enhancement approach is shifted from multi‐image fusion to target cropping and pasting. By introducing parameters to control the target pasting ratio and scaling ratio, the diversity of small target data and their size variations are enriched. Additionally, target size and type filters are added to enable targeted enhancement for different sizes and types of targets. This study, evaluates the proposed strategy using two representative traffic sign detection datasets, namely CTSD and GTSDB. The experimental results demonstrate a significant improvement in both detection and recognition performance of the model: on the CTSD dataset, the models trained with FlexibleCP data enhancement achieve 88.9% and 64.5% mAP0.5 and mAP0.5:0.95, respectively, which are 3.5% and 2.5% better than those trained with mosaic data enhancement; on the GTSDB dataset mAP0.5 and mAP0.5:0.95 reached 89.2% and 56.0%, respectively, an improvement of 4.0% and 3.9% over mosaic.

show abstract

A Comprehensive Survey of Imbalance Correction Techniques for Hyperspectral Data Classification

Paoletti

Mogollón

Moreno‐Álvarez

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

A Novel Multi-Sample Data Augmentation Method for Oriented Object Detection in Remote Sensing Images

Cited by 4 publications

References 42 publications

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

FlexibleCP: A data augmentation strategy for traffic sign detection

A Comprehensive Survey of Imbalance Correction Techniques for Hyperspectral Data Classification

Contact Info

Product

Resources

About