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

The continuous development of the photovoltaic (PV) industry has raised highrequirements for the quality of monocrystalline of PV module cells. Whenlearning to segment defect regions in PV module cell images, Tiny Hidden Cracks(THC) lead to extremely-imbalanced samples. The ratio of defect pixels tonormal pixels can be as low as 1:2000. This extreme imbalance makes itdifficult to segment the THC of PV module cells, which is also a challenge forsemantic segmentation. To address the problem of segmenting defects onextremely-imbalanced THC data, the paper makes contributions from threeaspects: (1) it proposes an explicit measure for output imbalance; (2) itgeneralizes a distribution-based loss that can handle different types of outputimbalances; and (3) it introduces a compound loss with our adaptivehyperparameter selection algorithm that can keep the consistency of trainingand inference for harmonizing the output imbalance on extremelyimbalanced inputdata. The proposed method is evaluated on four widely-used deep learningarchitectures and four datasets with varying degrees of input imbalance. Theexperimental results show that the proposed method outperforms existingmethods.

Harmonizing output imbalance for defect segmentation on extremely-imbalanced photovoltaic module cells images