Search

Convolutional neural networks (CNNs) have proved to achieve state-of-the-art performance in content-based remote sensing image retrieval (CBRSIR). However, CNNs cannot focus on discriminative features of important objects, resulting in unsatisfactory retrieval performance with complex backgrounds and small objects. We therefore propose a multi-attention fusion network with dilated convolution and label smoothing for CBRSIR. First, a dilated convolutional layer is used to replace the fifth convolutional layer in the network to obtain a large receptive field. Then, a contextual transformer attention (CoT) and an efficient channel attention (ECA) are fused together for spatial-wise and channel-wise discriminative features, respectively. The multi-attention module is embedded between the newly added dilated convolutional layer and the followed average pooling layer. Besides, in order to enhance the differences between the discriminative features of those correct and incorrect classes, label smoothing is used to replace the cross-entropy loss function. Some ablation experiments are conducted on six benchmark datasets. Compared to the baseline AlextNet with the above different modules, the mAP values of the proposed network improve by 14.84% to 24.21%. The results indicate that our network can significantly improve the retrieval performance. In addition, we have also conducted some experiments for network migration and comparison with some recent methods (e.g. a triplet deep metric learning and deep feature learning with latent relationship embedding network). Experimental results illustrate that our network can be effectively migrated to other similar CNN models and can achieve state-of-the-art or competitive results. [ABSTRACT FROM AUTHOR]

Benchmark datasets play an important role in evaluating remote sensing image retrieval (RSIR) methods. The current datasets cover many scene categories, but omit an important scene of color steel sheds, which are widely distributed with a large number on the earth's surface. Therefore, we propose a new benchmark dataset of color steel sheds (CSS) from Google map imagery for RSIR and share it open access in our V-RSIR system. The new dataset has rich intra-class and inter-class diversity, and is composed of blue, red and white color steel sheds with the total number of 2407 remote sensing images. We conduct evaluation experiments on the new dataset by using ten low/mid feature-based and ten deep learning feature-based methods. Experimental results indicate that the dataset is effective for evaluating RSIR methods and using the dataset can construct an effective retrieval model for color steel sheds. Besides, we have experimentally demonstrated that color constancy does affect retrieval performance on our CSS dataset. Furthermore, some experiments of merging the CSS dataset with the PatternNet, VGoogle and NWPU45 datasets are also conducted. Experimental results demonstrate that our dataset can be used as a complement to other retrieval datasets. Furthermore, these experimental results can be used as baseline for future applications on RSIR. [ABSTRACT FROM AUTHOR]