A Disjoint Samples-based 3D-CNN with Active Transfer Learning for Hyperspectral Image Classification

• Published in: IEEE transactions on geoscience and remote sensing Vol. 60; p. 1
• Main Authors: Ahmad, Muhammad, Ghous, Usman, Hong, Danfeng, Khan, Adil Mehmood, Yao, Jing, Wang, Shaohua, Chanussot, Jocelyn
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: 3D Convolutional Neural Network (3D CNN); Active Learning (AL); Artificial neural networks; Classification; Computational modeling; Computer applications; Convolutional neural networks; Costs; Engineering Sciences; Feature extraction; Hyperspectral Image Classification (HSIC); Hyperspectral imaging; Image classification; Iterative methods; Learning; Neural networks; Signal and Image processing; Solid modeling; Spatial-Spectral Information; Testing time; Three dimensional models; Three-dimensional displays; Training; Transfer Learning; Training; Solid modeling; Three-dimensional displays; Costs; Computational modeling; Feature extraction; Convolutional neural networks
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2022.3209182

Convolutional Neural Networks (CNNs) have been extensively studied for Hyperspectral Image Classification (HSIC). However, CNNs are critically attributed to a large number of labeled training samples, which outlays high costs in terms of time and resources. Moreover, CNNs are trained on some samples and have been tested on the entire HSI. Perhaps, the entire HSI is taken into account at test time to appropriately generate the ground truth maps. In order to obtain a higher accuracy while considering the limited availability of training samples and disjoint validation and test samples, this work proposes a fast and compact 3D CNN-based Active Learning (AL) for HSIC that integrates both deep transfer learning and AL into a unified framework. In the proposed methodology, a 3D CNN model is trained with very few training samples (i.e., 5%, only) and in the next phase, the most informative and heterogeneous samples are queried from the validation set (candidate set) based on the fuzziness, mutual information and breaking ties of the trained model. The 3D CNN model is later fine-tuned (rather retraining from scratch) with the new training samples (i.e., 200 samples are selected in each iteration) to reduce the computational cost. The proposed method has been compared with the state-of-the-art traditional and deep models proposed for HSIC. Experimental results proved the superiority of our proposed method on several benchmark HSI datasets with significantly fewer labeled samples. Matlab demo can be accessed on GitHub: github.com/mahmad00.