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

There has been significant attention devoted to the effectiveness of variousdomains, such as semi-supervised learning, contrastive learning, andmeta-learning, in enhancing the performance of methods for noisy label learning(NLL) tasks. However, most existing methods still depend on prior assumptionsregarding clean samples amidst different sources of noise (\eg, a pre-defineddrop rate or a small subset of clean samples). In this paper, we propose asimple yet powerful idea called \textbf{NPN}, which revolutionizes\textbf{N}oisy label learning by integrating \textbf{P}artial label learning(PLL) and \textbf{N}egative learning (NL). Toward this goal, we initiallydecompose the given label space adaptively into the candidate and complementarylabels, thereby establishing the conditions for PLL and NL. We propose twoadaptive data-driven paradigms of label disambiguation for PLL: harddisambiguation and soft disambiguation. Furthermore, we generate reliablecomplementary labels using all non-candidate labels for NL to enhance modelrobustness through indirect supervision. To maintain label reliability duringthe later stage of model training, we introduce a consistency regularizationterm that encourages agreement between the outputs of multiple augmentations.Experiments conducted on both synthetically corrupted and real-world noisydatasets demonstrate the superiority of NPN compared to other state-of-the-art(SOTA) methods. The source code has been made available at{\color{purple}{\url{https://github.com/NUST-Machine-Intelligence-Laboratory/NPN}}}.

Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning