An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
Sign Up to like & getrecommendations! Published in 2022 at "Entropy"
DOI: 10.3390/e24091303
Abstract: Contrastive learning is a representation learning method performed by contrasting a sample to other similar samples so that they are brought closely together, forming clusters in the feature space. The learning process is typically conducted… read more here.
Keywords: imbalanced datasets; handling imbalanced; loss; contrastive loss ... See more keywords