Image-to-image translation has made great strides in recent years, with current techniques being able to handle unpaired training images and to account for the multimodality of the translation problem. Despite this, most methods treat the image as a whole, which makes the results they produce for content-rich scenes less realistic. In this paper, we introduce a Detection-based Unsupervised Image-to-image Translation (DUNIT) approach that explicitly accounts for the object instances in the translation process. To this end, we extract separate representations for the global image and for the instances, which we then fuse into a common representation from which we generate the translated image. This allows us to preserve the detailed content of object instances, while still modeling the fact that we aim to produce an image of a single consistent scene. We introduce an instance consistency loss to maintain the coherence between the detections. Furthermore, by incorporating a detector into our architecture, we can still exploit object instances at test time. As evidenced by our experiments, this allows us to outperform the state-of-the-art unsupervised image-to-image translation methods. Furthermore, our approach can also be used as an unsupervised domain adaptation strategy for object detection, and it also achieves state-of-the-art performance on this task.
Selecting which blockchain participants can decide upon a new block is a difficult problem.Consortium blockchains need the participants to be predetermined while public blockchains incentivize all participants to waste their resources to decide every block. In this paper, we introduce the community blockchain that allows potentially all participants to decide upon ''some'' block while restricting the set of participants deciding upon ''one'' block. To this end, we propose a blockchain reconfiguration, a Byzantine consensus protocol that allows to dynamically change the set of blockchain participants deciding upon the upcoming blocks. The resulting blockchain, called ComChain, is resilience optimal and transitions through different configurations of participants recorded in dedicated blocks so that each configuration decides upon its subsequent transaction blocks. We evaluate an implementation that adds reconfiguration to the Red Belly Blockchain and demonstrates its practical performance in a distributed system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.