Semi-supervised bidirectional alignment for Remote Sensing cross-domain scene classification

Huang, Wei; Shi, Yilei; Xiong, Zhitong; Wang, Qi; Zhu, Xiao Xiang

doi:10.1016/j.isprsjprs.2022.11.013

Cited by 23 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, domain-adversarial neural networks (DANNs) [34], Siamese GAN [35], Attention GAN [10], and DA via a task-specific classifier (DATSNET) framework [36] are presented for the classification of remote sensing images, by learning an invariant representation. Recently, a multitude of closed-set DA algorithms for remote sensing image scene classification [37], [38], [39], [40], [41], [42], [43] is designed to reduce the global or local distribution differences between domains. In addition, closedset DA with multiple source domains [44] is proposed for remote sensing image classification.…”

Section: Related Workmentioning

confidence: 99%

Universal Domain Adaptation for Remote Sensing Image Scene Classification

Shi

Yuan

et al. 2023

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

The domain adaptation (DA) approaches available to date are usually not well suited for practical DA scenarios of remote sensing image classification since these methods (such as unsupervised DA) rely on rich prior knowledge about the relationship between label sets of source and target domains, and source data are often not accessible due to privacy or confidentiality issues. To this end, we propose a practical universal DA (UniDA) setting for remote sensing image scene classification that requires no prior knowledge on the label sets. Furthermore, a novel UniDA method without source data is proposed for cases when the source data are unavailable. The architecture of the model is divided into two parts: the source data generation stage and the model adaptation stage. The first stage estimates the conditional distribution of source data from the pretrained model using the knowledge of class separability in the source domain and then synthesizes the source data. With this synthetic source data in hand, it becomes a UniDA task to classify a target sample correctly if it belongs to any category in the source label set or mark it as "unknown" otherwise. In the second stage, a novel transferable weight that distinguishes the shared and private label sets in each domain promotes the adaptation in the automatically discovered shared label set and recognizes the "unknown" samples successfully. Empirical results show that the proposed model is effective and practical for remote sensing image scene classification, regardless of whether the source data are available or not. The code is available at

show abstract

Section: Related Workmentioning

confidence: 99%

Universal Domain Adaptation for Remote Sensing Image Scene Classification

Shi

Yuan

et al. 2023

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The featurebased DG includes domain-invariant representation learning and feature disentanglement. For example, Zhu et al [29] proposed a style and content separation network (SCSN) for cross-scene remote sensing image classification. By effectively disentangling and recognizing the style and content information, SCSN improves the model's generalization capability.…”

Section: B Related Work On Da and Dgmentioning

confidence: 99%

Triple Loss Adversarial Domain Adaptation Network for Cross-Domain Sea–Land Clutter Classification

Zhang,

Li,

Pan

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep learning (DL)-based sea-land clutter classification for sky-wave over-the-horizon-radar (OTHR) has become a novel research topic. In engineering applications, realtime predictions of sea-land clutter with existing distribution discrepancies are crucial. To solve this problem, this article proposes a novel Multisource Semisupervised Adversarial Domain Generalization Network (MSADGN) for cross-scene sea-land clutter classification. MSADGN can extract domain-invariant and domain-specific features from one labeled source domain and multiple unlabeled source domains, and then generalize these features to an arbitrary unseen target domain for real-time prediction of sea-land clutter. Specifically, MSADGN consists of three modules: domain-related pseudolabeling module, domaininvariant module, and domain-specific module. The first module introduces an improved pseudolabel method called domainrelated pseudolabel, which is designed to generate reliable pseudolabels to fully exploit unlabeled source domains. The second module utilizes a generative adversarial network (GAN) with a multidiscriminator to extract domain-invariant features, to enhance the model's transferability in the target domain. The third module employs a parallel multiclassifier branch to extract domain-specific features, to enhance the model's discriminability in the target domain. The effectiveness of our method is validated in twelve domain generalizations (DG) scenarios. Meanwhile, we selected 10 state-of-the-art DG methods for comparison. The experimental results demonstrate the superiority of our method.

show abstract

“…For example, domain-adversarial neural networks (DANN) [34], Siamese GAN [35], Attention GAN [10], and domain adaptation via a task-specific classifier (DATSNET) framework [36] are presented for the classification of remote sensing images, by learning an invariant representation. Recently, a multitude of closed-set DA algorithms for remote sensing image scene classification [37]- [43] is designed to reduce the global or local distribution differences between domains. In addition, closed-set DA with multiple source domains [44] is proposed for remote sensing image classification.…”

Section: Related Workmentioning

confidence: 99%

Universal Domain Adaptation without Source Data for Remote Sensing Image Scene Classification

Shi

Zhu

2022

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

Existing domain adaptation (DA) approaches are usually not well suited for practical DA scenarios of remote sensing image classification, since these methods (such as unsupervised DA) rely on rich prior knowledge about the relationship between label sets of source and target domains, and source data are usually not accessible in many cases due to the privacy or confidentiality issues. To this end, we propose a novel source data generation-based universal domain adaptation (SDG-UniDA) model, which includes two parts, i.e., the stage of source data generation and the stage of model adaptation. The first stage is to estimate the conditional distribution of source data from the pre-trained model using the knowledge of class-separability in the source domain and then to synthesize the source data. With this synthetic source data in hand, it becomes a universal DA task that requires no prior knowledge on the label sets. A novel transferable weight is proposed to distinguish the shared and private label sets to each domain, thereby promoting the adaptation in the automatically discovered shared label set and recognizing the "unknown" samples successfully. Empirical results show that SDG-UniDA is effective and practical in this challenging setting for remote sensing image scene classification.

show abstract

Semi-supervised bidirectional alignment for Remote Sensing cross-domain scene classification

Cited by 23 publications

References 43 publications

Universal Domain Adaptation for Remote Sensing Image Scene Classification

Universal Domain Adaptation for Remote Sensing Image Scene Classification

Triple Loss Adversarial Domain Adaptation Network for Cross-Domain Sea–Land Clutter Classification

Universal Domain Adaptation without Source Data for Remote Sensing Image Scene Classification

Contact Info

Product

Resources

About