Контрастная тонкая настройка

method ID: contrastivefinetuning

Related Papers

Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classification

Authors: nan

Publication: TIPSTER (2021)

DOI: nan

AbstractFine-grained classification involves dealing with datasets with larger number of classes with subtle differences between them. Guiding the model to focus on differentiating dimensions between these commonly confusable classes is …...

31746