English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Many real-world applications have to tackle the Positive-Unlabeled (PU)learning problem, i.e., learning binary classifiers from a large amount ofunlabeled data and a few labeled positive examples. While currentstate-of-the-art methods employ importance reweighting to design various riskestimators, they ignored the learning capability of the model itself, whichcould have provided reliable supervision. This motivates us to propose a novelSelf-PU learning framework, which seamlessly integrates PU learning andself-training. Self-PU highlights three "self"-oriented building blocks: aself-paced training algorithm that adaptively discovers and augments confidentpositive/negative examples as the training proceeds; a self-calibratedinstance-aware loss; and a self-distillation scheme that introducesteacher-students learning as an effective regularization for PU learning. Wedemonstrate the state-of-the-art performance of Self-PU on common PU learningbenchmarks (MNIST and CIFAR-10), which compare favorably against the latestcompetitors. Moreover, we study a real-world application of PU learning, i.e.,classifying brain images of Alzheimer's Disease. Self-PU obtains significantlyimproved results on the renowned Alzheimer's Disease Neuroimaging Initiative(ADNI) database over existing methods. The code is publicly available at:https://github.com/TAMU-VITA/Self-PU.

Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training