Thumbnail Image

Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval

Sumbul, Gencer; Ravanbakhsh, Mahdyar; Demir, Begüm

Learning the similarity between remote sensing (RS) images forms the foundation for content-based RS image retrieval (CBIR). Recently, deep metric learning approaches that map the semantic similarity of images into an embedding (metric) space have been found very popular in RS. A common approach for learning the metric space relies on the selection of triplets of similar (positive) and dissimilar (negative) images to a reference image called an anchor. Choosing triplets is a difficult task particularly for multilabel RS CBIR, where each training image is annotated by multiple class labels. To address this problem, in this article, we propose a novel triplet sampling method in the framework of deep neural networks (DNNs) defined for multilabel RS CBIR problems. The proposed method selects a small set of the most representative and informative triplets based on two main steps. In the first step, a set of anchors that are diverse to each other in the embedding space is selected from the current minibatch using an iterative algorithm. In the second step, different sets of positive and negative images are chosen for each anchor by evaluating the relevancy, hardness, and diversity of the images among each other based on a novel strategy. Experimental results obtained on two multilabel benchmark archives show that the selection of the most informative and representative triplets in the context of DNNs results in: 1) reducing the computational complexity of the training phase of the DNNs without any significant loss on the performance and 2) an increase in learning speed since informative triplets allow fast convergence. The code of the proposed method is publicly available at https://git.tu-berlin.de/rsim/image-retrieval-from-triplets .
Published in: IEEE Transactions on Geoscience and Remote Sensing, 10.1109/TGRS.2021.3124326, Institute of Electrical and Electronics Engineers (IEEE)