In recent years, fully supervised object detection methods in remote sensing images with good performance have been developed. However, this approach requires a large number of instance-level annotated samples that are relatively expensive to acquire. Therefore, weakly supervised learning using only image-level annotations has attracted much attention. Most of the weakly supervised object detection methods are based on multi-instance learning methods, and their performance depends on the process of scoring the candidate region proposals during training. In this process, the use of only image-level labels for supervision usually cannot obtain optimal results due to the lack of location information of the object. To address the above problem, a dynamic sample pseudo-label generation framework is proposed to generate pseudo-labels for each proposal without additional annotations. First, we propose the pseudo-label generation algorithm (PLG) to generate the category labels of the proposal by using the localization information of the object. Specifically, we propose to use the pixel average of the object’s localization map in the proposal as the proposal category confidence and calculate the pseudo-label by comparing the proposal category confidence with the preset threshold. In addition, an effective adaptive threshold selection strategy is designed to eliminate the effect of different category shape differences in computing sample pseudo-labels. Comparative experiments on the NWPU VHR-10 dataset demonstrate that our method can significantly improve the detection performance compared to existing methods.

Deep learning-based methods succeed in remote sensing scene classification (RSSC). However, current methods require training on a large dataset, and if a class does not appear in the training set, it does not work well. Zero-shot classification methods are designed to address the classification for unseen category images in which the generative adversarial network (GAN) is a popular method. Thus, our approach aims to achieve the zero-shot RSSC based on GAN. We employed the conditional Wasserstein generative adversarial network (WGAN) to generate image features. Since remote sensing images have inter-class similarity and intra-class diversity, we introduced classification loss, semantic regression module, and class-prototype loss to constrain the generator. The classification loss was used to preserve inter-class discrimination. We used the semantic regression module to ensure that the image features generated by the generator can represent the semantic features. We introduced class-prototype loss to ensure the intra-class diversity of the synthesized image features and avoid generating too homogeneous image features. We studied the effect of different semantic embeddings for zero-shot RSSC. We performed experiments on three datasets, and the experimental results show that our method performs better than the state-of-the-art methods in zero-shot RSSC in most cases.

Visualization of the small world network is an excellent challenge for classic layout algorithm, which is highly connected, resulting in the shape of the hairball. Backbone extraction method can simplify the classic layout to get better visualization, and it has become a significant approach in this field. However, contemporary approaches have two primary defects. Centrality based method loses plenty of topology information, and most contemporary approaches have the problem in low interactivity due to parameter sensibility. We proposed a backbone method based on interactive edge selection (IES-Backbone) to solve two problems for small world network visualization that mentioned above. The proposed method starts with backbone extraction of the network and then apply the layout algorithm to get visualization results. A critical approach of the backbone method is edge selection, which is based on the distance between vertices layout of the binary stress model. Edge selection makes the simplified network a clear community structure feature with more topological details. The simplified network is high in homophily and has closer average path length to the original network. The visualization result is controlled by edge limit ratio r and sampling rate s. Different choices of two parameters can change the results substantially on visual without affecting the layout quality, which proves high interactivity for users. Experiments prove that IES-Backbone is an interactive visualization method that presents community and sufficient topological features.

In recent years, entity-based ranking models have led to exciting breakthroughs in the research of information retrieval. Compared with traditional retrieval models, entity-based representation enables a better understanding of queries and documents. However, the existing entity-based models neglect the importance of entities in a document. This paper attempts to explore the effects of the importance of entities in a document. Specifically, the dataset analysis is conducted which verifies the correlation between the importance of entities in a document and document ranking. Then, this paper enhances two entity-based models—toy model and Explicit Semantic Ranking model (ESR)—by considering the importance of entities. In contrast to the existing models, the enhanced models assign the weights of entities according to their importance. Experimental results show that the enhanced toy model and ESR can outperform the two baselines by as much as 4.57% and 2.74% on NDCG@20 respectively, and further experiments reveal that the strength of the enhanced models is more evident on long queries and the queries where ESR fails, confirming the effectiveness of taking the importance of entities into account.

Heterogeneous graph neural networks (HGNNs) deliver the powerful capability to model many complex systems in real-world scenarios by embedding rich structural and semantic information of a heterogeneous graph into low-dimensional representations. However, existing HGNNs encounter great difficulty in balancing the ability to avoid artificial metapaths with resisting structural and informational noise in a heterogeneous graph. In this paper, we propose a novel framework called Heterogeneous Graph Purification Network (HGPN) which aims to solve such dilemma by adaptively purifying the noisy heterogeneity. Specifically, instead of relying on artificial metapaths, HGPN models heterogeneity by subgraph decomposition and adopts inter-subgraph and intra-subgraph aggregation methods. HGPN can learn to purify noisy edges based on semantic information with a parallel heterogeneous structure purification mechanism. Besides, we design a neighborhood-related dynamic residual update method, a type-specific normalization module and cluster-aware loss to help all types of node achieve high-quality representations and maintain feature distribution while preventing feature over-mixing problems. Extensive experiments are conducted on four common heterogeneous graph datasets, and results show that our approach outperforms all existing methods and achieves state-of-the-art performances consistently among all the datasets.