D
Danfeng Hong
Researcher at University of Grenoble
Publications - 13
Citations - 437
Danfeng Hong is an academic researcher from University of Grenoble. The author has contributed to research in topics: Computer science & Hyperspectral imaging. The author has an hindex of 5, co-authored 12 publications receiving 104 citations. Previous affiliations of Danfeng Hong include Chinese Academy of Sciences & Technische Universität München.
Papers
More filters
Journal ArticleDOI
Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixing.
TL;DR: In this article, the authors proposed an end-member-guided unmixing network (EGU-Net), which is a two-stream Siamese deep network that learns an additional network from the pure or nearly pure endmembers to correct the weights of another unmixer by sharing network parameters and adding spectrally meaningful constraints.
Journal ArticleDOI
Multimodal GANs: Toward Crossmodal Hyperspectral–Multispectral Image Segmentation
TL;DR: This article introduces two novel plug-and-play units in the network: self-generative adversarial networks (GANs) module and mutual-GANs module, to learn perturbation-insensitive feature representations and to eliminate the gap between multimodalities, respectively, yielding more effective and robust information transfer.
Journal ArticleDOI
Deep point embedding for urban classification using ALS point clouds: A new perspective from local to global
TL;DR: This paper proposes a novel method for obtaining semantic labels of airborne laser scanning (ALS) point clouds involving the embedding of local context information for each point with multi-scale deep learning, nonlinear manifold learning for feature dimension reduction, and global graph-based optimization for refining the classification results.
Journal ArticleDOI
Learning Convolutional Sparse Coding on Complex Domain for Interferometric Phase Restoration
TL;DR: This article proposes an alternative approach for InSAR phase restoration, that is, Complex Convolutional Sparse Coding (ComCSC) and its gradient regularized version and can not only suppress interferometric phase noise, but also avoid the staircase effect and preserve the details.
Journal ArticleDOI
CyCU-Net: Cycle-Consistency Unmixing Network by Learning Cascaded Autoencoders
TL;DR: This work proposes a cycle-consistency unmixing network, called CyCU-Net, capable of reducing the detailed and material-related information loss in the process of reconstruction by relaxing the original pixel-level reconstruction assumption to cycle consistency dominated by the cascaded AEs.