Global Optimal Structured Embedding Learning for Remote Sensing Image Retrieval
Open Access
Abstract
A rich line of works focus on designing elegant loss functions under the deep metric learning (DML) paradigm to learn a discriminative embedding space for remote sensing image retrieval (RSIR). Essentially, such embedding space could efficiently distinguish deep feature descriptors. So far, most existing losses used in RSIR are based on triplets, which have disadvantages of local optimization, slow convergence and insufficient use of similarity structure in a mini-batch. In this paper, we present a novel DML method named as global optimal structured loss to deal with the limitation of triplet loss. To be specific, we use a softmax function rather than a hinge function in our novel loss to realize global optimization. In addition, we present a novel optimal structured loss, which globally learn an efficient deep embedding space with mined informative sample pairs to force the positive pairs within a limitation and push the negative ones far away from a given boundary. We have conducted extensive experiments on four public remote sensing datasets and the results show that the proposed global optimal structured loss with pairs mining scheme achieves the state-of-the-art performance compared with the baselines.Keywords
Funding Information
- Nature Science Foundation of China (61841602)
This publication has 68 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Performance Analysis of State-of-the-Art Representation Methods for Geographical Image Retrieval and CategorizationIEEE Geoscience and Remote Sensing Letters, 2014
- Shape-based Invariant Texture IndexingInternational Journal of Computer Vision, 2009
- Random Forests for land cover classificationPattern Recognition Letters, 2006
- Information mining in remote sensing image archives: system conceptsIEEE Transactions on Geoscience and Remote Sensing, 2003
- An environment for content-based image retrieval from large spatial databasesISPRS Journal of Photogrammetry and Remote Sensing, 1999
- Spatial information retrieval from remote-sensing images. II. Gibbs-Markov random fieldsIEEE Transactions on Geoscience and Remote Sensing, 1998
- Spatial information retrieval from remote-sensing images. I. Information theoretical perspectiveIEEE Transactions on Geoscience and Remote Sensing, 1998
- Texture features for browsing and retrieval of image dataIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Similarity Metric Learning for a Variable-Kernel ClassifierNeural Computation, 1995