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

Due to the costliness of labelled data in real-world applications,semi-supervised learning, underpinned by pseudo labelling, is an appealingsolution. However, handling confusing samples is nontrivial: discardingvaluable confusing samples would compromise the model generalisation whileusing them for training would exacerbate the issue of confirmation bias causedby the resulting inevitable mislabelling. To solve this problem, this paperproposes to use confusing samples proactively without label correction.Specifically, a Virtual Category (VC) is assigned to each confusing sample insuch a way that it can safely contribute to the model optimisation even withouta concrete label. This provides an upper bound for inter-class informationsharing capacity, which eventually leads to a better embedding space. Extensiveexperiments on two mainstream dense prediction tasks -- semantic segmentationand object detection, demonstrate that the proposed VC learning significantlysurpasses the state-of-the-art, especially when only very few labels areavailable. Our intriguing findings highlight the usage of VC learning in densevision tasks.

Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels