Domain Adaptive Remote Sensing Scene Recognition via Semantic Relationship Knowledge Transfer

Zhao, Ying Na; Li, Shuang; Liu, Chi Harold; Han, Yan; Shi, Hao; Li, Wei

doi:10.1109/tgrs.2023.3267149

Cited by 5 publications

(2 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feature clustering effect can effectively reflect the classification results, and the Distributed Stochastic Neighbor Embedding (t-SNE) [45] technique is a very effective feature visualization display method [46]. Therefore, t-SNE is used to visualize the distribution of the target dataset.…”

Section: F Visual Analysismentioning

confidence: 99%

Domain Adaptive Remote Sensing Scene Classification With Middle-Layer Feature Extraction and Nuclear Norm Maximization

Du,

Wang,

Zhang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) methods have become a research hotspot in remote sensing scene classification to reduce dependence on labeled samples. However, most current methods focus on extracting domain invariant features, ignoring the problem of large intra-class differences and the imbalanced sample numbers between categories in remote sensing images. To address these issues, we propose a remote sensing scene domain adaptive method based on middle-layer feature extraction and nuclear norm maximization (MFE-NM). In the MFE module, the middle-layer features of the feature extractor are randomly extracted and processed. Since the receptive field of the middle-layer features is smaller and the resolution is higher, the effective use of the middle-layer features can reduce the impact of image feature heterogeneity caused by large intraclass differences in remote sensing images. In addition, it can be concluded that the constrained nuclear norm can simultaneously improve the prediction diversity and discriminability of the model through theoretical derivation. Therefore, the NM module is proposed to solve the problem of reduced prediction diversity caused by entropy minimization methods when dealing with scene classification problems with imbalanced sample numbers between categories. Extensive experiments and analyses on three public remote sensing datasets demonstrate the effectiveness and competitiveness of our proposed method.

show abstract

Section: F Visual Analysismentioning

confidence: 99%

Domain Adaptive Remote Sensing Scene Classification With Middle-Layer Feature Extraction and Nuclear Norm Maximization

Du,

Wang,

Zhang

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Yang et al [14] achieved better distributional alignment by dynamically adjusting the comparative importance of the marginal and conditional distributions during the domain alignment process. Zhao et al [33] focused on the mining of intrinsic associations in the scene by conveying the knowledge of semantic relationships between the source and target domains to effectively boost the model's performance in the target domain. Focusing on the semi-supervised domain adaptation task, ref.…”

Section: Cross-domain Scene Classificationmentioning

confidence: 99%

Cross-Domain Classification Based on Frequency Component Adaptation for Remote Sensing Images

Zhu,

Zhang,

Han

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Cross-domain scene classification requires the transfer of knowledge from labeled source domains to unlabeled target domain data to improve its classification performance. This task can reduce the labeling cost of remote sensing images and improve the generalization ability of models. However, the huge distributional gap between labeled source domains and unlabeled target domains acquired by different scenes and different sensors is a core challenge. Existing cross-domain scene classification methods focus on designing better distributional alignment constraints, but are under-explored for fine-grained features. We propose a cross-domain scene classification method called the Frequency Component Adaptation Network (FCAN), which considers low-frequency features and high-frequency features separately for more comprehensive adaptation. Specifically, the features are refined and aligned separately through a high-frequency feature enhancement module (HFE) and a low-frequency feature extraction module (LFE). We conducted extensive transfer experiments on 12 cross-scene tasks between the AID, CLRS, MLRSN, and RSSCN7 datasets, as well as two cross-sensor tasks between the NWPU-RESISC45 and NaSC-TG2 datasets, and the results show that the FCAN can effectively improve the model’s performance for scene classification on unlabeled target domains compared to other methods.

show abstract

Domain Adaptation for Multilabel Remote Sensing Image Annotation With Contrastive Pseudo-Label Generation

Huang,

Ma,

Huang

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Domain Adaptive Remote Sensing Scene Recognition via Semantic Relationship Knowledge Transfer

Cited by 5 publications

References 61 publications

Domain Adaptive Remote Sensing Scene Classification With Middle-Layer Feature Extraction and Nuclear Norm Maximization

Domain Adaptive Remote Sensing Scene Classification With Middle-Layer Feature Extraction and Nuclear Norm Maximization

Cross-Domain Classification Based on Frequency Component Adaptation for Remote Sensing Images

Domain Adaptation for Multilabel Remote Sensing Image Annotation With Contrastive Pseudo-Label Generation

Contact Info

Product

Resources

About