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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Training deep neural networks (DNNs) in the presence of noisy labels is animportant and challenging task. Probabilistic modeling, which consists of aclassifier and a transition matrix, depicts the transformation from true labelsto noisy labels and is a promising approach. However, recent probabilisticmethods directly apply transition matrix to DNN, neglect DNN's susceptibilityto overfitting, and achieve unsatisfactory performance, especially under theuniform noise. In this paper, inspired by label smoothing, we proposed a novelmethod, in which a smoothed transition matrix is used for updating DNN, torestrict the overfitting of DNN in probabilistic modeling. Our method is termedMatrix Smoothing. We also empirically demonstrate that our method not onlyimproves the robustness of probabilistic modeling significantly, but also evenobtains a better estimation of the transition matrix.

Matrix Smoothing: A Regularization for DNN with Transition Matrix under Noisy Labels