Published in International Journal of Applied Earth Observation and Geoinformation, 2024
This paper is about the universal adversarial defense in remote sensing, which utilized a DDPM model to defend the deep learning models against the adversarial perturbations.
Download here
Published in arxiv preprint, 2024
This paper develops a mining change detection benchmark consists of a mining change detection dataset, a ChangeFFT-based model, and a unified change detection framework.
Download here
Published in IEEE Transactions on Geoscience and Remote Sensing, 2024
This paper develops a change detection network based on mask classification.
Download here
Published in arxiv preprint, 2024
This paper comprehensively reviews the responsibility of current AI for earth observation schemes, with considerations of privacy, ethical concerns, security, and unfair biases, and the obejct of AI for social good.
Download here
Published in IEEE Transactions on Image Processing, 2023
This paper proposes a novel text-to-image modern Hopfield network (Txt2Img-MHN) to conduct hierarchical prototype learning on both text and image embeddings with modern Hopfield layers.
Download here
Published in IEEE Geoscience and Remote Sensing Magazine, 2023
This paper provides a systematic review of AI security-related research in the geoscience and remote sensing community.
Download here
Published in IEEE Geoscience and Remote Sensing Letters, 2023
This paper proposes a local–global anchor guidance network (LGAGNet) for weakly supervised landslide extraction.
Download here
Published in ISPRS Journal of Photogrammetry and Remote Sensing, 2023
This paper proposes a prototype-guided domain-aware progressive representation learning (PG-DPRL) method for cross-domain landslide mapping from large-scale remote sensing images based on the multitarget domain adaptation (MTDA) technique.
Download here
Published in IEEE Transactions on Geoscience and Remote Sensing, 2023
This paper proposes a novel federated learning scheme with prototype matching (FedPM) to collaboratively learn a richer DCNN model by leveraging remote sensing data distributed among multiple clients.
Download here
Published in IEEE Transactions on Geoscience and Remote Sensing, 2022
This paper proposes multilevel deformable attention-aggregated networks (MLDANets) to effectively learn long-range dependencies across multiple levels of bitemporal convolutional features for multiscale context aggregation.
Download here
Published in IEEE Geoscience and Remote Sensing Letters, 2022
This paper proposes a multiscale distortion-aware cloud removal (MSDA-CR) network consisting of multiple cloud-distortion-aware representation learning (CDARL) modules combined in a multiscale grid architecture.
Download here
Published in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, 2021
This paper proposes a novel Cloud Aware and Feature Extraction (CAFE) module by incorporating the physical model of cloud distortion considering atmosphere light, cloud reflectance light and cloud transmission.
Download here
Published in 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, Brussels, Belgium, 2021
This paper proposes an object-level boundary-preserving generative adversarial network (BPGAN) for style transformation-based CD of bi-temporal images.
Download here