DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval

Abstract

With a small number of labeled samples for training, it can save considerable manpower and material resources, especially when the amount of high spatial resolution remote sensing images (HSR-RSIs) increases considerably. However, many deep models face the problem of overfitting when using a small number of labeled samples. This might degrade HSRRSI retrieval accuracy. Aiming at obtaining more accurate HSR-RSI retrieval performance with small training samples, we develop a deep metric learning approach with generative adversarial network regularization (DML-GANR) for HSR-RSI retrieval. The DML-GANR starts from a high-level feature extraction (HFE) to extract high-level features, which includes convolutional layers and fully connected (FC) layers. Each of the FC layers is constructed by deep metric learning (DML) to maximize the interclass variations and minimize the intraclass variations. The generative adversarial network (GAN) is adopted to mitigate the overfitting problem and validate the qualities of extracted high-level features. DML-GANR is optimized through a customized approach, and the optimal parameters are obtained. The experimental results on the three data sets demonstrate the superior performance of DML-GANR over state-of-the-art techniques in HSR-RSI retrieval.

arXiv comment17 pages

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep learning in remote sensing: a review
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
• PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval
• Land Use Classification in Remote Sensing Images by Convolutional Neural Networks
• MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
• Learning Low Dimensional Convolutional Neural Networks for High-Resolution Remote Sensing Image Retrieval
• Binary Generative Adversarial Networks for Image Retrieval
• Large Scale Strongly Supervised Ensemble Metric Learning, with Applications to Face Verification and Retrieval