Difference-Guided Aggregation Network With Multiimage Pixel Contrast for Change Detection
- 22 May 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-14
Abstract
Change detection is a critical task in remote sensing to monitor the state of the surface on Earth. This field has been dominated by deep learning-based methods recently. Many models that model the temporal-spatial correlation in bitemporal images through the non-local interaction between bitemporal features achieve impressive performance. However, under complex scenes including multiple change types or weakly discriminate objects, they suffer from achieving discriminative fusion of information due to the weak semantic discrimination of the bitemporal representations. Aiming at this problem, a difference-guided aggregation network (DGANet) is proposed, where two key modules are injected, i.e., a difference-guided aggregation module (DGAM) and a weighted metric module (WMM). The bitemporal features in DGAM are aggregated with the guidance of their differences, which focuses on their change relevance and relaxes their semantic distinction. Therefore, the fused features are change-relevant and discriminative. WMM aims to achieve adaptive distance computation between the bitemporal features by dynamic feature attention in different dimensions. It is helpful to suppress the pseudo-changes. Besides, a change magnitude contrastive loss (CMCL) is introduced to employ the dependency of bitemporal pixels in different bitemporal images, which further enhances the representation quality of the model. Meanwhile, it is further extended in this work. The effectiveness of the three improvements is demonstrated by extensive ablation studies. The results on three datasets widely used illustrate that our method achieves satisfactory performance.Keywords
Funding Information
- National Natural Science Foundation of China (U21B2041, 61825603)
- National Key Research and Development Program of China (2020YFB2103902)
This publication has 49 references indexed in Scilit:
- Separate segmentation of multi-temporal high-resolution remote sensing images for object-based change detection in urban areaRemote Sensing of Environment, 2017
- Change Detection Based on Deep Siamese Convolutional Network for Optical Aerial ImagesIEEE Geoscience and Remote Sensing Letters, 2017
- A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar ImagesIEEE Transactions on Neural Networks and Learning Systems, 2016
- Fault-Tolerant Building Change Detection From Urban High-Resolution Remote Sensing ImageryIEEE Geoscience and Remote Sensing Letters, 2013
- Support Vector Reduction in SVM Algorithm for Abrupt Change Detection in Remote SensingIEEE Geoscience and Remote Sensing Letters, 2009
- PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite dataInternational Journal of Remote Sensing, 2008
- Change vector analysis: A technique for the multispectral monitoring of land cover and conditionInternational Journal of Remote Sensing, 1998
- Digital change detection in forest ecosystems with remote sensing imageryRemote Sensing Reviews, 1996
- Monitoring urban land cover changes at the urban fringe from SPOT HRV imagery in south-east EnglandInternational Journal of Remote Sensing, 1989
- Procedures for change detection using Landsat digital dataInternational Journal of Remote Sensing, 1981