In this paper, we propose a wide contextual residual network (WCRN) with active learning (AL) for remote sensing image (RSI) classification. Although ResNets have achieved great success in various applications (e.g. RSI classification), its performance is limited by the requirement of abundant labeled samples. As it is very difficult and expensive to obtain class labels in real world, we integrate the proposed WCRN with AL to improve its generalization by using the most informative training samples. Specifically, we first design a wide contextual residual network for RSI classification. We then integrate it with AL to achieve good machine generalization with limited number of training sampling. Experimental results on the University of Pavia and Flevoland datasets demonstrate that the proposed WCRN with AL can significantly reduce the needs of samples.

Large scale semantic graphs such as social networks and knowledge graphs contain rich and useful information. However, due to combined challenges in scale, density, and heterogeneity, it is impractical for users to answer many interesting questions by visual inspection alone. This is because even a semantically simple question, such as which of my extended friends are also fans of my favorite band, can in fact require information from a non-trivial number of nodes to answer. In this paper, we propose a method that combines graph browsing with query to overcome the limitation of visual inspection. By using query as the main way for information discovery in graph exploration, our “query, expand, and query again” model enables users to probe beyond the visible part of the graph and only bring in the interesting nodes, leaving the view clutter-free. We have implemented a prototype called GraphCharter and demonstrated its effectiveness and usability in a case study and a user study on Freebase knowledge graph with millions of nodes and edges.

Focus+Context is a popular and effective technique for graph exploration. While previous works concentrate on studying how to display focal nodes with a single context, we argue that it is often difficult to select an optimal context for a complex graph exploration task in practice. In this paper, we propose Multi-Con, a technique to allow users viewing multiple contexts to explore graphs more effectively and efficiently. Our idea is to let users define multiple contexts to reveal different aspects of the graph and enable users to switch between these contexts quickly and interactively in a single view during exploration. Multi-Con provides two key features to ensure the effectiveness and efficiency when using multiple contexts for graph exploration. First, it can achieve good legibility when displaying foci with each context in limited viewing space. In addition, it allows users to switch between contexts smoothly and quickly. We have conducted a case study with social network data extracted from paper authorship relations on three major conferences in computer architecture and systems areas. The results have shown that Multi-Con can help users quickly learn the relationship between foci and the rest of the network in multiple aspects.

The treemap is one of the most popular methods for visualizing hierarchical data. When a treemap contains a large number of items, inspecting or comparing a few selected items in a greater level of detail becomes very challenging. In this paper, we present a seamless multi-focus and context technique, called Balloon Focus, that allows the user to smoothly enlarge multiple treemap items served as the foci, while maintaining a stable treemap layout as the context. Our method has several desirable features. First, this method is quite general and hence can be used with different treemap layout algorithms. Second, as the foci are enlarged, the relative positions among all items are preserved. Third, the foci are placed in a way that the remaining space is evenly distributed back to the non-focus treemap items. When Balloon Focus enlarges the focus items to a maximum degree, the above features ensure that the treemap will maintain a consistent appearance and avoid any abrupt layout changes. In our algorithm, a DAG (Directed Acyclic Graph) is used to maintain the positional constraints, and an elastic model is employed to govern the placement of the treemap items. We demonstrate a treemap visualization system that integrates data query, manual focus selection, and our novel multi-focus+context technique, Balloon Focus, together. A user study was conducted. Results show that with Balloon Focus, users can better perform the tasks of comparing the values and the distribution of the foci.

While the treemap is a popular method for visualizing hierarchical data, it is often difficult for users to track layout and attribute changes when the data evolve over time. When viewing the treemaps side by side or back and forth, there exist several problems that can prevent viewers from performing effective comparisons. Those problems include abrupt layout changes, a lack of prominent visual patterns to represent layouts, and a lack of direct contrast to highlight differences. In this paper, we present strategies to visualize changes of hierarchical data using treemaps. A new treemap layout algorithm is presented to reduce abrupt layout changes and produce consistent visual patterns. Techniques are proposed to effectively visualize the difference and contrast between two treemap snapshots in terms of the map items' colors, sizes, and positions. Experimental data show that our algorithm can achieve a good balance in maintaining a treemap's stability, continuity, readability, and average aspect ratio. A software tool is created to compare treemaps and generate the visualizations. User studies show that the users can better understand the changes in the hierarchy and layout, and more quickly notice the color and size differences using our method.