Robust Instance-Based Semi-Supervised Learning Change Detection for Remote Sensing Images
- 20 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Abstract
Semi-supervised change detection (SSCD) has experienced rapid development, with numerous semi-supervised methods being proposed to reduce the reliance on labeled data in change detection. Existing approaches typically rely on manually set high-confidence thresholds to select robust pseudo-labels. However, the single-pixel threshold filtering method for pseudo-labels (STFP) lacks context correlation, cannot eliminate high-confidence false positive samples, and leads to erroneously filtering out low-confidence true positive samples. To address this issue, we propose robust instance-based semi-supervised learning change detection (RISL) for remote sensing images. RISL evaluates the reliability of each instance object by linking the semantic information of the context, thereby generating robust pseudo-labels. In RISL, firstly, a simple boundary trimming module (BT) as a preprocessing method for change prediction map is introduced. BT can effectively remove low-confidence false positive samples while avoiding confusion in the category of instance objects, thereby improving the quality of instance objects. Then, we propose a reliable instance evaluation module (RIEM) to evaluate the reliability of each instance object. RIEM combines the semantic information of the entire instance and establishes correlations between sample contexts to determine the reliability of the instance, effectively eliminating high false positive samples. In addition, the consistency regularization (CR) is integrated into RISL, and a new strategy suitable for RIEM is constructed. This strategy enhances the model’s generalization ability by mining and hiding semantic information from different views of unlabeled data. Experimental results on the challenging WHU-CD, LEVIR-CD, and CDD-CD datasets show that the proposed method achieves 89.80%, 90.01%, and 87.56% F1 scores on labeled data with 5% distribution. RISL achieves state-of-the-art performance compared to other methods.Keywords
Funding Information
- Key Scientific Technological Innovation Research Project by Ministry of Education
- State Key Program and the Foundation for Innovative Research Groups of the National Natural Science Foundation of China (61836009)
- Joint Funds of the National Natural Science Foundation of China (U22B2054)
- National Natural Science Foundation of China (62076192, 62006177, 61902298, 61573267, 61906150, 62276199)
- Higher Education Discipline Innovation Project
- Program for Cheung Kong Scholars and Innovative Research Team in University (IRT 15R53)
- ST Innovation Project from the Chinese Ministry of Education
- Key Research and Development Program in Shaanxi Province of China (2019ZDLGY03-06)
- National Science Basic Research Plan in Shaanxi Province of China (2022JQ-607)
- China Postdoctoral Fund (2022T150506)
This publication has 53 references indexed in Scilit:
- Learning consensus-aware semantic knowledge for remote sensing image captioningPattern Recognition, 2023
- Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation2023
- Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation2023
- Temporal Fusion Transformers for interpretable multi-horizon time series forecastingInternational Journal of Forecasting, 2021
- Integrating remote sensing and machine learning into environmental monitoring and assessment of land use changeSustainable Production and Consumption, 2021
- Semi-supervised Semantic Segmentation with Directional Context-aware Consistency2021
- Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-AnalysisIEEE Access, 2020
- A time-series classification approach based on change detection for rapid land cover mappingISPRS Journal of Photogrammetry and Remote Sensing, 2019
- CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features2019
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation2019