C²F²: Cross-Task Cross-Domain Feature Fusion for Semi-Supervised Change Detection
- 25 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21 (1545598X) , 1-5
Abstract
Semi-supervised learning for change detection (CD), which significantly reduces the labor costs associated with data annotation, has recently garnered substantial attention. In this study, we propose to enhance traditional semi-supervised learning frameworks by leveraging cross-task cross-domain (CTCD) models, which generate complementary features that differ from standard hidden features. The procedure is as follows. Firstly, the standard features obtained from a traditional encoding-decoding structure are fused with attention-augmented complementary features. Secondly, a secondary decoder maps the fused heterogeneous features into the label space to obtain high-quality pseudo-labels, offering more precise guidance for semi-supervised learning on traditional structures. This approach improves pseudo-labels by leveraging the strength of CTCD models, including large pre-trained models, to enhance the semi-supervised learning process of domain-specific and task-specific models. Experimental results on benchmark datasets demonstrate that our proposed approach surpasses state-of-the-art methods.Keywords
Funding Information
- Ningbo Science and Technology Innovation Project (2023CX050006)
- Ningbo Science and Technology Innovation Project (2022Z075)
This publication has 24 references indexed in Scilit:
- STCRNet: A Semi-Supervised Network Based on Self-Training and Consistency Regularization for Change Detection in VHR Remote Sensing ImagesIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023
- Exchange means change: An unsupervised single-temporal change detection framework based on intra- and inter-image patch exchangeISPRS Journal of Photogrammetry and Remote Sensing, 2023
- Compact Intertemporal Coupling Network for Remote Sensing Change Detection2023
- A Transformer-Based Siamese Network for Change Detection2022
- Randaugment: Practical automated data augmentation with a reduced search space2020
- Land-cover classification with high-resolution remote sensing images using transferable deep modelsRemote Sensing of Environment, 2020
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation2019
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Squeeze-and-Excitation Networks2018
- Pyramid Scene Parsing Network2017