Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or individuals. Recently, self-supervision has emerged as an alternative to leveraging unlabeled data. In this paper, we propose a new light-weight self-supervised learning framework that could boost supervised learning performance with minimum additional computation cost. Here, we introduce a simple and flexible multi-task co-training framework that integrates a self-supervised task into any supervised task. Our approach exploits pretext tasks to incur minimum compute and parameter overheads and minimal disruption to existing training pipelines. We demonstrate the effectiveness of our framework by using two self-supervised tasks, object detection and panoptic segmentation, on different perception models. Our results show that both self-supervised tasks can improve the accuracy of the supervised task and, at the same time, demonstrates strong domain adaption capability when used with additional unlabeled data.

The emerging prosperity of cryptocurrencies, such as Bitcoin, has come into the spotlight during the past few years. Cryptocurrency exchanges, which act as the gateway to this world, now play a dominant role in the circulation of Bitcoin. Thus, delving into the analysis of the transaction patterns of exchanges can shed light on the evolution and trends in the Bitcoin market, and participants can gain hints for identifying credible exchanges as well. Not only Bitcoin practitioners but also researchers in the financial domains are interested in the business intelligence behind the curtain. However, the task of multiple exchanges exploration and comparisons has been limited owing to the lack of efficient tools. Previous methods of visualizing Bitcoin data have mainly concentrated on tracking suspicious transaction logs, but it is cumbersome to analyze exchanges and their relationships with existing tools and methods. In this paper, we present BitExTract, an interactive visual analytics system, which, to the best of our knowledge, is the first attempt to explore the evolutionary transaction patterns of Bitcoin exchanges from two perspectives, namely, exchange versus exchange and exchange versus client. In particular, BitExTract summarizes the evolution of the Bitcoin market by observing the transactions between exchanges over time via a massive sequence view. A node-link diagram with ego-centered views depicts the trading network of exchanges and their temporal transaction distribution. Moreover, BitExTract embeds multiple parallel bars on a timeline to examine and compare the evolution patterns of transactions between different exchanges. Three case studies with novel insights demonstrate the effectiveness and usability of our system.

Skyline queries have wide-ranging applications in fields that involve multi-criteria decision making, including tourism, retail industry, and human resources. By automatically removing incompetent candidates, skyline queries allow users to focus on a subset of superior data items (i.e., the skyline), thus reducing the decision-making overhead. However, users are still required to interpret and compare these superior items manually before making a successful choice. This task is challenging because of two issues. First, people usually have fuzzy, unstable, and inconsistent preferences when presented with multiple candidates. Second, skyline queries do not reveal the reasons for the superiority of certain skyline points in a multi-dimensional space. To address these issues, we propose SkyLens, a visual analytic system aiming at revealing the superiority of skyline points from different perspectives and at different scales to aid users in their decision making. Two scenarios demonstrate the usefulness of SkyLens on two datasets with a dozen of attributes. A qualitative study is also conducted to show that users can efficiently accomplish skyline understanding and comparison tasks with SkyLens.