DDIPNet and DDIPNet+: Discriminant Deep Image Prior Networks for Remote Sensing Image Classification
This work addresses the need for reliable automation in remote sensing for tasks like urban planning and agriculture, representing an incremental improvement in domain-specific methods.
The paper tackled remote sensing image classification by proposing two novel deep learning architectures, DDIPNet and DDIPNet+, which combine Deep Image Prior and Triplet Networks. Experiments on three public datasets achieved state-of-the-art results, demonstrating the effectiveness of this approach.
Research on remote sensing image classification significantly impacts essential human routine tasks such as urban planning and agriculture. Nowadays, the rapid advance in technology and the availability of many high-quality remote sensing images create a demand for reliable automation methods. The current paper proposes two novel deep learning-based architectures for image classification purposes, i.e., the Discriminant Deep Image Prior Network and the Discriminant Deep Image Prior Network+, which combine Deep Image Prior and Triplet Networks learning strategies. Experiments conducted over three well-known public remote sensing image datasets achieved state-of-the-art results, evidencing the effectiveness of using deep image priors for remote sensing image classification.