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

Semi-supervised learning (SSL) improves model generalization by leveragingmassive unlabeled data to augment limited labeled samples. However, currently,popular SSL evaluation protocols are often constrained to computer vision (CV)tasks. In addition, previous work typically trains deep neural networks fromscratch, which is time-consuming and environmentally unfriendly. To address theabove issues, we construct a Unified SSL Benchmark (USB) for classification byselecting 15 diverse, challenging, and comprehensive tasks from CV, naturallanguage processing (NLP), and audio processing (Audio), on which wesystematically evaluate the dominant SSL methods, and also open-source amodular and extensible codebase for fair evaluation of these SSL methods. Wefurther provide the pre-trained versions of the state-of-the-art neural modelsfor CV tasks to make the cost affordable for further tuning. USB enables theevaluation of a single SSL algorithm on more tasks from multiple domains butwith less cost. Specifically, on a single NVIDIA V100, only 39 GPU days arerequired to evaluate FixMatch on 15 tasks in USB while 335 GPU days (279 GPUdays on 4 CV datasets except for ImageNet) are needed on 5 CV tasks withTorchSSL.

USB: A Unified Semi-supervised Learning Benchmark for Classification