Separable Coupled Dictionary Learning for Large-Scene Precise Classification of Multispectral Images

Liu, Tianzhu; Gu, Yanfeng; Yu, Wei; Jia, Xiuping; Chanussot, Jocelyn

doi:10.1109/tgrs.2022.3217061

Cited by 6 publications

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [20] proposed a class-guided coupled dictionary-learning method that utilizes the labels of training samples to construct discriminative sparse representation coefficient errors and classification errors as regularization terms, so as to effectively construct the compact and discriminative coupled dictionaries for HSI reconstruction. Liu et al [21] proposed a method that uses the labels of training samples to construct both class-specific coupled dictionaries and mutually coupled dictionaries, in order to focus on the class-specificity characteristics instead of mutuality characteristics, which is beneficial to classification.…”

Section: Spectral Super-resolution Based On Dictionary Learningmentioning

confidence: 99%

A Multi-Hyperspectral Image Collaborative Mapping Model Based on Adaptive Learning for Fine Classification

Zhang,

Liu,

Zhang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral (HS) data, encompassing hundreds of spectral channels for the same area, offer a wealth of spectral information and are increasingly utilized across various fields. However, their limitations in spatial resolution and imaging width pose challenges for precise recognition and fine classification in large scenes. Conversely, multispectral (MS) data excel in providing spatial details for vast landscapes but lack spectral precision. In this article, we proposed an adaptive learning-based mapping model, including an image fusion module, spectral super-resolution network, and adaptive learning network. Spectral super-resolution networks learn the mapping between multispectral and hyperspectral images based on the attention mechanism. The image fusion module leverages spatial and spectral consistency in training data, providing pseudo labels for spectral super-resolution training. And the adaptive learning network incorporates spectral response priors via unsupervised learning, adjusting the output of the super-resolution network to preserve spectral information in reconstructed data. Through the experiment, the model eliminates the need for the manual setting of image prior information and complex parameter selection, and can adjust the network structure and parameters dynamically, eventually enhancing the reconstructed image quality, and enabling the fine classification of large-scale scenes with high spatial resolution. Compared with the recent dictionary learning and deep learning spectral super-resolution methods, our approach exhibits superior performance in terms of both image similarity and classification accuracy.

show abstract

Section: Spectral Super-resolution Based On Dictionary Learningmentioning

confidence: 99%

A Multi-Hyperspectral Image Collaborative Mapping Model Based on Adaptive Learning for Fine Classification

Zhang,

Liu,

Zhang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…emote sensing scene classification, as an essential tool for interpreting remote sensing images, aims to categorize images into different scene classes by analyzing the features of objects in the images. In recent years, the rapid development of deep learning techniques, particularly the application of Convolutional Neural Networks (CNNs), has significantly advanced remote sensing scene classification and garnered widespread attention in the academic community [1], [2], [3], [4], [5], [6]. However, the success of deep learning models relies heavily on time-consuming and expensive data annotation.…”

Section: Introductionmentioning

confidence: 99%

Cross-Scene Classification of Remote Sensing Images Based on General-Specific Prototype Contrastive Learning

Chen,

Qiu,

Guo

et al. 2024

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

View full text Add to dashboard Cite

In recent years, constrained by the challenges associated with expensive data annotation and poor generalization ability in supervised models, domain adaptation has been proposed to effectively mitigate domain gaps, which has gained significant attention in the field of remote sensing. However, most existing methods do not consider the inherent characteristics of remote sensing images when formulating adaptive strategies. Additionally, there has been limited research on addressing classimbalanced data situations, leading to undesirable performance in domain adaptation tasks involving long-tailed datasets. To overcome the aforementioned limitations, based on the analysis of intra-class diversity and intra-domain style differences of remote sensing images, we propose a novel prototype contrastive learning framework called general-specific prototype contrastive learning (GSPCL). Due to the unreliability of clustering samples in conventional prototype-based clustering methods, the Bidirectional Weighted Prototype (BWP) strategy is proposed to optimize this loophole. Consequently, more robust prototypes are constructed in both domains, serving as mediators to reduce domain discrepancies bidirectionally. Particularly, often overlooked in most methods, we incorporate low-confidence sample features into the contrastive learning process alongside these prototypes, to further guide the model to address feature alignment and long-tail issues effectively. Finally, in order to verify the superiority of our proposed method, we adhere to two existing experiment settings and construct an extra optical remote sensing domain adaptation dataset with class-imbalanced scenarios. In the first two experimental settings, GSPCL outperforms the second-ranked approach by 5.0% and 4.0% in average accuracy. Furthermore, our approach exhibits highly competitive results in handling long-tailed data scenarios.

show abstract

Block Diagonal Representation Learning for Hyperspectral Band Selection

Liu

Fang

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Separable Coupled Dictionary Learning for Large-Scene Precise Classification of Multispectral Images

Cited by 6 publications

References 43 publications

A Multi-Hyperspectral Image Collaborative Mapping Model Based on Adaptive Learning for Fine Classification

A Multi-Hyperspectral Image Collaborative Mapping Model Based on Adaptive Learning for Fine Classification

Cross-Scene Classification of Remote Sensing Images Based on General-Specific Prototype Contrastive Learning

Block Diagonal Representation Learning for Hyperspectral Band Selection

Contact Info

Product

Resources

About