Collaborative Contrastive Learning for Hyperspectral and LiDAR Classification

Jia, Sen; Zhou, Xiaoming; Jiang, Shuguo; He, Ruyan

doi:10.1109/tgrs.2023.3263511

Cited by 19 publications

(2 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the aforementioned methods highly improve the efficiency and contribution of unlabeled data in RS CD tasks, random data augmentation is still required to construct pseudocontrastive sample pairs when performing self-supervised pretraining [69,70,71,72]. Uncertainty may be introduced during this process, causing fluctuations in model performance.…”

Section: B Self-supervised Contrastive Learning In CD Taskmentioning

confidence: 99%

SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptation

Zhao,

Celik,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Section: B Self-supervised Contrastive Learning In CD Taskmentioning

confidence: 99%

SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptation

Zhao,

Celik,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Zhang et al [44] implemented feature extraction by a 3D CNN and applied contrastive learning to learn more discriminative features so as to address the high interclass similarity and large intra-class variance of HSIs. Jia et al [45] designed a collaborative contrastive learning strategy to learn coordinated representations and achieve matching between LiDAR and HSI without labeled examples. This strategy adequately fused the LiDAR and hyperspectral data and effectively enhanced the classification accuracy of HSI and LiDAR data.…”

Section: Contrastive Learningmentioning

confidence: 99%

A Dual-Attention Deep Discriminative Domain Generalization Model for Hyperspectral Image Classification

Zhao,

Wang,

Wang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Recently, hyperspectral image classification has made great progress with the development of convolutional neural networks. However, due to the challenges of distribution shifts and data redundancies, the classification accuracy is low. Some existing domain adaptation methods try to mitigate the distribution shifts by training source samples and some labeled target samples. However, in practice, labeled target domain samples are difficult or even impossible to obtain. To solve the above challenges, we propose a novel dual-attention deep discriminative domain generalization framework (DAD3GM) for cross-scene hyperspectral image classification without training the labeled target samples. In DAD3GM, we mainly design two blocks: dual-attention feature learning (DAFL) and deep discriminative feature learning (DDFL). DAFL is designed to extract spatial features by multi-scale self-attention and extract spectral features by multi-head external attention. DDFL is further designed to extract deep discriminative features by contrastive regularization and class discrimination regularization. The combination of DAFL and DDFL can effectively reduce the computational time and improve the generalization performance of DAD3GM. The proposed model achieves 84.25%, 83.53%, and 80.63% overall accuracy on the public Houston, Pavia, and GID benchmarks, respectively. Compared with some classical and state-of-the-art methods, the proposed model achieves optimal results, which reveals its effectiveness and feasibility.

show abstract

Multiscale Neighborhood Information Fusion Network for Classification of Remote Sensing LiDAR Images

Dong,

Liu,

Han

et al. 2024

IEEE Sensors J.

View full text Add to dashboard Cite

Collaborative Contrastive Learning for Hyperspectral and LiDAR Classification

Cited by 19 publications

References 53 publications

SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptation

SSLChange: A Self-supervised Change Detection Framework Based on Domain Adaptation

A Dual-Attention Deep Discriminative Domain Generalization Model for Hyperspectral Image Classification

Multiscale Neighborhood Information Fusion Network for Classification of Remote Sensing LiDAR Images

Contact Info

Product

Resources

About