• Home
  • Search
  • AdaAug+: A Reinforcement Learning-Based Adaptive Data Augmentation for Change Detection
  • https://doi.org/10.1109/tgrs.2024.3478218Copy DOI Icon

AdaAug+: A Reinforcement Learning-Based Adaptive Data Augmentation for Change Detection

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Data augmentation (DA) increases the diversity of training data to improve the model generalization ability. Most of the DA methods focus on image classification or object detection. Directly using the existing DA methods on change detection tasks not only falls short of fully exploring the specificity of the change image pairs but also leads to longer training times. In this article, we first propose a mask-guided mixing (MGM) DA for change detection, which mixes the change regions of the current training sample based on prediction results and labels to generate high-quality samples with more positive samples. We then propose a new reinforcement learning (RL)-based Adaptive DA method, AdaAug+, to adaptively select the optimal DA policy for the training samples. An actor selects the best augmentation operation from the operation set according to the image pair. The augmented image pairs make it easier for the change detector to learn the optimal parameters and improve the final detection performance. To reduce the training time, we identify and remove the redundant training samples during the training process by our redundancy searching policy. We have conducted various experiments on four remote sensing change detection datasets with different change detectors. The experimental results demonstrate that AdaAug+ achieves promising performance compared to the state-of-the-art DA methods and requires less training time.

Similar Papers
  • Research Article
  • Citations30

Soft Augmentation-Based Siamese CNN for Hyperspectral Image Classification With Limited Training Samples

  • Jan 01, 2022
  • IEEE Geoscience and Remote Sensing Letters
  • Weiquan Wang +3
  • PDF
  • Research Article
  • Citations14

Smart(Sampling)Augment: Optimal and Efficient Data Augmentation for Semantic Segmentation

  • May 16, 2022
  • Algorithms
  • Misgana Negassi +2
  • Research Article
  • Citations3

AdaAugment: A Tuning-Free and Adaptive Approach to Enhance Data Augmentation.

  • Jan 01, 2025
  • IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • Suorong Yang +4
  • Research Article
  • Citations32

Discriminative feature constraints via supervised contrastive learning for few-shot forest tree species classification using airborne hyperspectral images

  • Jul 07, 2023
  • Remote Sensing of Environment
  • Long Chen +4
  • Research Article
  • Citations9

Improving Alzheimer’s disease classification using novel rewards in deep reinforcement learning

  • Oct 12, 2024
  • Biomedical Signal Processing and Control
  • Mahla Hatami +2
  • PDF
  • Research Article
  • Citations2

Attention-ProNet: A Prototype Network with Hybrid Attention Mechanisms Applied to Zero Calibration in Rapid Serial Visual Presentation-Based Brain–Computer Interface

  • Apr 02, 2024
  • Bioengineering
  • Baiwen Zhang +4
  • Conference Article
  • Citations44

STaDA: Style Transfer as Data Augmentation

  • Jan 01, 2019
  • Xu Zheng +4
  • Conference Article
  • Citations9

Domain-specific data augmentation for on-road object detection based on a deep neural network

  • Jun 01, 2017
  • Hui Eun Kim +3
  • Research Article
  • Citations1

IPF-RDA: An Information-Preserving Framework for Robust Data Augmentation.

  • Feb 01, 2026
  • IEEE transactions on pattern analysis and machine intelligence
  • Suorong Yang +4
  • Research Article
  • Citations69

Effect of data-augmentation on fine-tuned CNN model performance

  • Mar 01, 2021
  • IAES International Journal of Artificial Intelligence (IJ-AI)
  • Ramaprasad Poojary +2
  • Research Article
  • Citations13

A Novel Environmentally Robust ODDM Detection Approach Using Contrastive Learning

  • Sep 01, 2023
  • IEEE Transactions on Communications
  • Qingqing Cheng +4
  • Research Article
  • Citations9

Intelligent Diagnosis Method for Typical Co-frequency Vibration Faults of Rotating Machinery Based on SAE and Ensembled ResNet-SVM

  • Jul 15, 2024
  • Chinese Journal of Mechanical Engineering
  • Xiancheng Zhang +3
  • PDF
  • Research Article
  • Citations36

Feature transforms for image data augmentation

  • Aug 22, 2022
  • Neural Computing and Applications
  • Loris Nanni +3
  • Research Article
  • Citations33

Erasing-inpainting-based data augmentation using denoising diffusion probabilistic models with limited samples for generalized surface defect inspection

  • Dec 30, 2023
  • Mechanical Systems and Signal Processing
  • Huanjie Tao
  • PDF
  • Research Article
  • Citations2

A Chinese–Kazakh Translation Method That Combines Data Augmentation and R-Drop Regularization

  • Sep 22, 2023
  • Applied Sciences
  • Canglan Liu +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.