Three-Layer Convex Network for Domain Adaptation in Multitemporal VHR Images

Othman, Esam; Bazi, Yakoub; Alajlan, Naif; Alhichri, Haikel; Melgani, Farid

doi:10.1109/lgrs.2015.2512999

Cited by 9 publications

(10 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [50], the authors consider the domains as multidimensional graphs and propose to align the domains by solving a graph-matching problem. Finally, the authors in [51] find a multispectral mapping between source and target spectra to project the labeled pixels of the source domain into the target domain. Tie points are found between the labeled source pixels and the pixels in the target by registration, and then the mapping between the source and target is learned by regression between the corresponding pairs.…”

Section: Adapting Data Distributionsmentioning

confidence: 99%

“…Finally, authors in [51] find a multispectral mapping between source and target spectra, in order to project the labeled pixels of the source into the target domain: tie points are found between the labeled source pixels and the pixels in the target by registration and then the mapping between source and target is learned by regression between the corresponding pairs. Then, the labeled pixels are projected into the target domain and are used to train a classifier therein.…”

Section: B Adapting Data Distributionsmentioning

confidence: 99%

See 1 more Smart Citation

Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances

Tuia

Persello

Bruzzone

2016

IEEE Geosci. Remote Sens. Mag.

450

213

View full text Add to dashboard Cite

jUNE 2016 ieee Geoscience and remote sensinG maGazine 0274-6638/16©2016IEEE 41 T he success of the supervised classification of remotely sensed images acquired over large geographical areas or at short time intervals strongly depends on the representativity of the samples used to train the classification algorithm and to define the model. When training samples are collected from an image or a spatial region that is different from the one used for mapping, spectral shifts between the two distributions are likely to make the model fail. Such shifts are generally due to differences in acquisition and atmospheric conditions or to changes in the nature of the object observed. To design classification methods that are robust to data set shifts, recent remote sensing literature has considered solutions based on domain adaptation (DA) approaches. Inspired by machine-learning literature, several DA methods have been proposed to solve specific problems in remote sensing data classification. This article provides a critical review of the recent advances in DA approaches for remote sensing and presents an overview of DA methods divided into four categories: 1) invariant feature selection, 2) representation matching, 3) adaptation of classifiers, and 4) selective sampling. We provide an overview of recent

show abstract

Section: Adapting Data Distributionsmentioning

confidence: 99%

Section: B Adapting Data Distributionsmentioning

confidence: 99%

Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances

Tuia

Persello

Bruzzone

2016

IEEE Geosci. Remote Sens. Mag.

450

213

View full text Add to dashboard Cite

show abstract

“…Manifold alignment techniques proposed in [20][21][22][23][24] also focus on projecting samples from both domains into a common space while preserving local manifold structures of the datasets during the transformation. In [25], the authors proposed a three-layer domain adaptation technique for a multi-temporal very high resolution (VHR) image classification problem. The proposed layers are composed of two extreme learning machine (ELM) layers, one for regression and the other for multi-class classification, followed by a spatial regularization layer based on the random walker algorithm [26].…”

Section: Introductionmentioning

confidence: 99%

Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

Bejiga

Melgani

Beraldini³

2019

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Learning classification models require sufficiently labeled training samples, however, collecting labeled samples for every new problem is time-consuming and costly. An alternative approach is to transfer knowledge from one problem to another, which is called transfer learning. Domain adaptation (DA) is a type of transfer learning that aims to find a new latent space where the domain discrepancy between the source and the target domain is negligible. In this work, we propose an unsupervised DA technique called domain adversarial neural networks (DANNs), composed of a feature extractor, a class predictor, and domain classifier blocks, for large-scale land cover classification. Contrary to the traditional methods that perform representation and classifier learning in separate stages, DANNs combine them into a single stage, thereby learning a new representation of the input data that is both domain-invariant and discriminative. Once trained, the classifier of a DANN can be used to predict both source and target domain labels. Additionally, we also modify the domain classifier of a DANN to evaluate its suitability for multi-target domain adaptation problems. Experimental results obtained for both single and multiple target DA problems show that the proposed method provides a performance gain of up to 40%.

show abstract

“…(3) adaptation of classifiers; and (4) selective sampling. Nevertheless, all these methods [20][21][22][23][24] are designed for annotation transfer between remote sensing images. With an increasing amount of freely available ground level images with detailed tags, one interesting and possible intuition is that we can train semantic scene models using ground view images, as they have already been collected and annotated, and hope that the models still work well on overhead-view aerial or satellite scene images.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification

Deng

Sun

Zhou

2018

IJGI

View full text Add to dashboard Cite

Currently, huge quantities of remote sensing images (RSIs) are becoming available. Nevertheless, the scarcity of labeled samples hinders the semantic understanding of RSIs. Fortunately, many ground-level image datasets with detailed semantic annotations have been collected in the vision community. In this paper, we attempt to exploit the abundant labeled ground-level images to build discriminative models for overhead-view RSI classification. However, images from the ground-level and overhead view are represented by heterogeneous features with different distributions; how to effectively combine multiple features and reduce the mismatch of distributions are two key problems in this scene-model transfer task. Specifically, a semi-supervised manifold-regularized multiple-kernel-learning (SMRMKL) algorithm is proposed for solving these problems. We employ multiple kernels over several features to learn an optimal combined model automatically. Multi-kernel Maximum Mean Discrepancy (MK-MMD) is utilized to measure the data mismatch. To make use of unlabeled target samples, a manifold regularized semi-supervised learning process is incorporated into our framework. Extensive experimental results on both cross-view and aerial-to-satellite scene datasets demonstrate that: (1) SMRMKL has an appealing extension ability to effectively fuse different types of visual features; and (2) manifold regularization can improve the adaptation performance by utilizing unlabeled target samples.

show abstract

Three-Layer Convex Network for Domain Adaptation in Multitemporal VHR Images

Cited by 9 publications

References 9 publications

Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances

Domain Adaptation for the Classification of Remote Sensing Data: An Overview of Recent Advances

Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

Semi-Supervised Ground-to-Aerial Adaptation with Heterogeneous Features Learning for Scene Classification

Contact Info

Product

Resources

About