Imbalanced data poses challenges in generalizing models, especially in regression tasks. ConR introduces a contrastive regularizer to prevent features of minority samples from collapsing into majority ones. It effectively translates label relationships to the feature space, boosting performance on deep imbalanced regression benchmarks. The method is efficient, orthogonal to existing approaches, and extends seamlessly to uni- and multi-dimensional label spaces.
toiselle kielelle
lähdeaineistosta
arxiv.org
Tärkeimmät oivallukset
by Mahsa Kerama... klo arxiv.org 03-15-2024
https://arxiv.org/pdf/2309.06651.pdfSyvällisempiä Kysymyksiä