Supervised and unsupervised learning has seldom joined with and thus lend strength to each other in the field of Chinese word segmentation (CWS). This paper presents a novel approach to CWS that utilizes description length gain (DLG), an empirical goodness measure for unsupervised word discovery, to enhance the segmentation performance of conditional random field (CRF) learning. Specifically, w...

The visual attributes of cells, such as the nuclear morphology and chromatin openness, are critical for histopathology image analysis. By learning cell-level visual representation, we can obtain a rich mix of features that are highly reusable for various tasks, such as cell-level classification, nuclei segmentation, and cell counting. In this paper, we propose a unified generative adversarial n...

This report consists of a literature review of papers dealing with object recognition using unsupervised learning techniques. Five papers that brought important contributions to the field are summarized, analyzed and compared. It was found that unsupervised object recognition was considered first as an image segmentation problem, but new unsupervised object learning techniques have been develop...

Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, which policy is first pre-trained with interactions, and then fine-tuned towards the optimal for several downstream supervised tasks defined over same environment. Along this line, we address problem of class multiple environments, interactions from whole class, any environment class. Notabl...