Academic Journal
Objective evaluation-based efficient learning framework for hyperspectral image classification
| العنوان: | Objective evaluation-based efficient learning framework for hyperspectral image classification |
|---|---|
| المؤلفون: | Xuming Zhang, Jian Yan, Jia Tian, Wei Li, Xingfa Gu, Qingjiu Tian |
| المصدر: | GIScience & Remote Sensing, Vol 60, Iss 1 (2023) |
| بيانات النشر: | Taylor & Francis Group, 2023. |
| سنة النشر: | 2023 |
| المجموعة: | LCC:Mathematical geography. Cartography LCC:Environmental sciences |
| مصطلحات موضوعية: | deep learning, fully convolutional network, features extraction, sampling strategy, Mathematical geography. Cartography, GA1-1776, Environmental sciences, GE1-350 |
| الوصف: | Deep learning techniques with remarkable performance have been successfully applied to hyperspectral image (HSI) classification. Due to the limited availability of training data, earlier studies primarily adopted the patch-based classification framework, which divides images into overlapping patches for training and testing. However, this framework results in redundant computations and possible information leakage. This study proposes an objective evaluation-based efficient learning framework for HSI classification. It consists of two main parts: (i) a leakage-free balanced sampling strategy and (ii) an efficient fully convolutional network (EfficientFCN) optimized for the accuracy-efficiency trade-off. The leakage-free balanced sampling strategy first generates balanced and non-overlapping training and test data by partitioning the HSI and its ground truth image into non-overlapping windows. Then, the generated training and test data are used to train and test the proposed EfficientFCN. EfficientFCN exhibits a pixel-to-pixel architecture with modifications for faster inference speed and improved parameter efficiency. Experimental results demonstrate that the proposed sampling strategy can provide objective performance evaluation. EfficientFCN outperforms many state-of-the-art approaches concerning the speed-accuracy trade-off. For instance, compared to the recent efficient models EfficientNetV2 and ConvNeXt, EfficientFCN achieves 0.92% and 3.42% superior accuracy and 0.19s and 0.16s faster inference time, respectively, on the Houston dataset. Code is available at https://github.com/xmzhang2018. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 1548-1603 1943-7226 15481603 |
| Relation: | https://doaj.org/toc/1548-1603; https://doaj.org/toc/1943-7226 |
| DOI: | 10.1080/15481603.2023.2225273 |
| URL الوصول: | https://doaj.org/article/870e603544d640aeb8a29b59cd86e227 |
| رقم الانضمام: | edsdoj.870e603544d640aeb8a29b59cd86e227 |
| قاعدة البيانات: | Directory of Open Access Journals |
| تدمد: | 15481603 19437226 |
|---|---|
| DOI: | 10.1080/15481603.2023.2225273 |