Most of the approaches used for Landslide inventory mapping (LIM) rely on traditional feature extraction and unsupervised classification algorithms. However, it is difficult to use these approaches to detect landslide areas because of the complexity and spatial uncertainty of landslides. In this letter, we propose a novel approach based on a fully convolutional network within pyramid pooling (FCN-PP) for LIM. The proposed approach has three advantages. First, this approach is automatic and insensitive to noise because multivariate morphological reconstruction is used for image preprocessing. Second, it is able to take into account features from multiple convolutional layers and explore efficiently the context of images, which leads to a good tradeoff between wider receptive field and the use of context. Finally, the selected PP module addresses the drawback of global pooling employed by convolutional neural network, FCN, and U-Net, and, thus, provides better feature maps for landslide areas. Experimental results show that the proposed FCN-PP is effective for LIM, and it outperforms the state-of-the-art approaches in terms of five metrics, Precision, Recall, Overall Error, F-score, and Accuracy.

Recently, many researchers have been dedicated to using convolutional neural networks (CNNs) to extract global-context features (GCFs) for remote-sensing scene classification. Commonly, accurate classification of scenes requires knowledge about both the global context and local objects. However, unlike the natural images in which the objects cover most of the image, objects in remote-sensing images are generally small and decentralized. Thus, it is hard for vanilla CNNs to focus on both global context and small local objects. To address this issue, this paper proposes a novel end-to-end CNN by integrating the GCFs and local-object-level features (LOFs). The proposed network includes two branches, the local object branch (LOB) and global semantic branch (GSB), which are used to generate the LOFs and GCFs, respectively. Then, the concatenation of features extracted from the two branches allows our method to be more discriminative in scene classification. Three challenging benchmark remote-sensing datasets were extensively experimented on; the proposed approach outperformed the existing scene classification methods and achieved state-of-the-art results for all three datasets.

A hyperspectral image (HSI) includes a vast quantity of samples, a large number of bands, and randomly occurring redundancy. Classifying such complex data is challenging, and its classification performance can be affected significantly by the amount of labeled training samples, as well as the quality, position, and others factors of these samples. Collecting such labeled training samples is labor and time consuming, motivating the idea of taking advantage of labeled samples from other pre-existing related images. Therefore, transfer learning, which can mitigate the semantic gap between existing and new HSIs, has drawn increasing research attention. However, existing transfer learning methods for HSIs (which mainly concentrate on how to overcome the divergence among images) may fail to carefully consider the contents to be transferred and thus limit their performances. In this paper, we present two novel ideas: 1) we, for the first time, introduce an active learning process to initialize the salient samples on the HSI data, which would be transferred later; and 2) we propose constructing and connecting higher level features for the source and target HSI data to further overcome the cross-domain disparity. Different from existing methods, the proposed framework requires no a priori knowledge on the target domain, and it works for both homogeneous and heterogeneous HSI data. Experimental results on three real-world HSIs support the effectiveness of the proposed method for HSI classification.

Graph-based and manifold-regularization (MR)-based semisupervised learning, including Laplacian regularization (LapR) and hypergraph LapR (HLapR), have achieved prominent performance in preserving locality and similarity information. However, it is still a great challenge to exactly explore and exploit the local structure of the data distribution. In this paper, we present an efficient and effective approximation algorithm of hypergraph ${p}$ -Laplacian and then propose hypergraph ${p}$ -LapR (HpLapR) to preserve the geometry of the probability distribution. In particular, hypergraph is a generalization of a standard graph while hypergraph ${p}$ -Laplacian is a nonlinear generalization of the standard graph Laplacian. The proposed HpLapR shows great potential to exploit the local structures. We integrate HpLapR with logistic regression for remote sensing image recognition. Experiments on UC-Merced data set demonstrate that the proposed HpLapR has superior performance compared with several popular MR methods including LapR and HLapR.

In this study, the authors address a challenging problem of aesthetic image classification, which is to label an input image as high‐ or low‐aesthetic quality. We take both the local and global features of images into consideration. A novel deep convolutional neural network named ILGNet is proposed, which combines both the inception modules and a connected layer of both local and global features. The ILGnet is based on GoogLeNet. Thus, it is easy to use a pre‐trained GoogLeNet for large‐scale image classification problem and fine tune their connected layers on a large‐scale database of aesthetic‐related images: AVA, i.e. domain adaptation . The experiments reveal that their model achieves the state of the arts in AVA database. Both the training and testing speeds of their model are higher than those of the original GoogLeNet.