Exploring Balanced Feature Spaces for Representation Learning

By Bingyi Kang, Yu Li, Saining Xie, Zehuan Yuan, Jiashi Feng. International Conference on Learning Representations, 2021

303 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Text Transformations in Contrastive Self-Supervised Learning: A Review (2022, methodology): “Moreover, for some specific objectives such as measuring the balancedness of a feature space, they rely on the linear separability performance which is evaluated by the accuracy of a linear classifier over the representation vectors [Kang et al., 2020; Jiang et al., 2021].”