DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval
This addresses the challenge of efficient and accurate image retrieval in remote sensing with limited labeled data, which is incremental as it builds on existing deep metric learning and GAN methods.
The paper tackles the problem of overfitting in deep models for high spatial resolution remote sensing image retrieval when using small labeled training samples, and develops DML-GANR, which combines deep metric learning with GAN regularization to achieve superior performance over state-of-the-art techniques on three datasets.
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.