Abstract: In this letter we revisit the famous heavy ball method and study its global convergence for a class of non-convex problems with sector-bounded gradient. We characterize the parameters that ...

This letter addresses the challenge of open-set instance segmentation (OSIS) which segments both known objects and unknown objects not seen in training, and thus is essential for enabling robots to ...

Most static website generators have technologies, conventions and source code layout requirements that you have to follow. Instead this is a framework and a collection of pipes and processes to build ...

Abstract: Few-shot learning is proposed to tackle the problem of scarce training data in novel classes. However, prior works in instance-level few-shot learning have paid less attention to effectively ...