When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNs

• Published in: IEEE transactions on geoscience and remote sensing Vol. 56; no. 5; pp. 2811 - 2821
• Main Authors: Cheng, Gong, Yang, Ceyuan, Yao, Xiwen, Guo, Lei, Han, Junwei
• Format: Journal Article
• Language: English
• Published: New York IEEE 01-05-2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Classification; Computer architecture; Convolutional neural networks (CNNs); Datasets; Deep learning; Detection; discriminative CNNs (D-CNNs); Entropy; Feature extraction; Image classification; Image color analysis; Learning systems; Machine learning; Measurement; Methods; metric learning; Neural networks; Objective function; Regularization; Remote sensing; remote sensing image scene classification; State of the art
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2017.2783902

Remote sensing image scene classification is an active and challenging task driven by many applications. More recently, with the advances of deep learning models especially convolutional neural networks (CNNs), the performance of remote sensing image scene classification has been significantly improved due to the powerful feature representations learnt through CNNs. Although great success has been obtained so far, the problems of within-class diversity and between-class similarity are still two big challenges. To address these problems, in this paper, we propose a simple but effective method to learn discriminative CNNs (D-CNNs) to boost the performance of remote sensing image scene classification. Different from the traditional CNN models that minimize only the cross entropy loss, our proposed D-CNN models are trained by optimizing a new discriminative objective function. To this end, apart from minimizing the classification error, we also explicitly impose a metric learning regularization term on the CNN features. The metric learning regularization enforces the D-CNN models to be more discriminative so that, in the new D-CNN feature spaces, the images from the same scene class are mapped closely to each other and the images of different classes are mapped as farther apart as possible. In the experiments, we comprehensively evaluate the proposed method on three publicly available benchmark data sets using three off-the-shelf CNN models. Experimental results demonstrate that our proposed D-CNN methods outperform the existing baseline methods and achieve state-of-the-art results on all three data sets.