CADR-BL: Class-Adaptive Dictionary Reconstruction with Broad Learning for Few-Shot Hyperspectral Image Classification.
Saved in:
| Title: | CADR-BL: Class-Adaptive Dictionary Reconstruction with Broad Learning for Few-Shot Hyperspectral Image Classification. |
|---|---|
| Authors: | Li, Ziwei1,2,3 (AUTHOR), Guo, Jiali1,2,3 (AUTHOR), Zhang, Weizhen3,4 (AUTHOR) weizhen@stu.haut.edu.cn, Han, Mengya1,2,3,4 (AUTHOR), Xu, Zhenqiang5 (AUTHOR), Zhang, Baowei6 (AUTHOR), Li, Ning1,2,3,7 (AUTHOR), Luo, Weiran1,2,3 (AUTHOR), Xie, Menglei2,7 (AUTHOR), Guo, Jianzhong1,2,3 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 9, p1263. 25p. |
| Subjects: | Machine learning, Image recognition (Computer vision), Generalization, Precision farming |
| Abstract: | Highlights: What are the main findings? A novel class-adaptive dictionary reconstruction (CADR) method is proposed to enhance intra-class spectral consistency and suppress inter-class feature interference in few-shot hyperspectral image classification. The proposed CADR-BL method combines CADR with the broad learning system, achieving superior classification performance on three public datasets (IP, SA and HC) under the condition of extremely limited training samples. What are the implications of the main findings? This method provides an effective and computationally efficient solution for few-shot hyperspectral image classification, balancing the feature representation capability and overfitting risk without relying on deep architectures. By improving category-level feature discriminability, CADR-BL offers a promising solution for practical applications with few labeled data, such as precision agriculture and urban monitoring. Hyperspectral image (HSI) classification in few-shot scenarios faces two core challenges. Limited samples and high spectral similarity lead to insufficient inter-class feature discriminability, and commonly used deep models suffer from the risk of overfitting. To address these problems, this paper proposes a Class-Adaptive Dictionary Reconstruction with Broad Learning (CADR-BL) method. Specifically, the method constructs an exclusive adaptive dictionary for each category and adopts an alternating minimization strategy to achieve sparse reconstruction of intra-class pixels, thereby enhancing intra-class spectral consistency and suppressing inter-class interference. On this basis, an improved Hyperspectral Broad Learning (HS-BL) model is introduced to efficiently classify the reconstructed features. Random feature mapping and closed-form solutions of output weights are utilized to alleviate overfitting in few-shot learning. Experiments conducted on three benchmark datasets, namely Indian Pines, Salinas, and WHU-Hi-HanChuan, show that CADR-BL outperforms several mainstream few-shot classification methods in terms of overall accuracy, average accuracy, and Kappa coefficient. Notably, CADR-BL maintains robust performance even with extremely limited training samples, and is less sensitive to variations in sample size than other comparative methods, demonstrating strong generalization ability. The proposed method provides a reliable technical reference for few-shot HSI classification in applications such as precision agriculture, environmental monitoring, and resource exploration. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? A novel class-adaptive dictionary reconstruction (CADR) method is proposed to enhance intra-class spectral consistency and suppress inter-class feature interference in few-shot hyperspectral image classification. The proposed CADR-BL method combines CADR with the broad learning system, achieving superior classification performance on three public datasets (IP, SA and HC) under the condition of extremely limited training samples. What are the implications of the main findings? This method provides an effective and computationally efficient solution for few-shot hyperspectral image classification, balancing the feature representation capability and overfitting risk without relying on deep architectures. By improving category-level feature discriminability, CADR-BL offers a promising solution for practical applications with few labeled data, such as precision agriculture and urban monitoring. Hyperspectral image (HSI) classification in few-shot scenarios faces two core challenges. Limited samples and high spectral similarity lead to insufficient inter-class feature discriminability, and commonly used deep models suffer from the risk of overfitting. To address these problems, this paper proposes a Class-Adaptive Dictionary Reconstruction with Broad Learning (CADR-BL) method. Specifically, the method constructs an exclusive adaptive dictionary for each category and adopts an alternating minimization strategy to achieve sparse reconstruction of intra-class pixels, thereby enhancing intra-class spectral consistency and suppressing inter-class interference. On this basis, an improved Hyperspectral Broad Learning (HS-BL) model is introduced to efficiently classify the reconstructed features. Random feature mapping and closed-form solutions of output weights are utilized to alleviate overfitting in few-shot learning. Experiments conducted on three benchmark datasets, namely Indian Pines, Salinas, and WHU-Hi-HanChuan, show that CADR-BL outperforms several mainstream few-shot classification methods in terms of overall accuracy, average accuracy, and Kappa coefficient. Notably, CADR-BL maintains robust performance even with extremely limited training samples, and is less sensitive to variations in sample size than other comparative methods, demonstrating strong generalization ability. The proposed method provides a reliable technical reference for few-shot HSI classification in applications such as precision agriculture, environmental monitoring, and resource exploration. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18091263 |
