Description
RotNet is a self-supervision approach that relies on predicting image rotations as the pretext task in order to learn image representations.
Papers Using This Method
ScaleNet: An Unsupervised Representation Learning Method for Limited Information2023-10-03Test-time Training for Data-efficient UCDR2022-08-19Self-supervised Detransformation Autoencoder for Representation Learning in Open Set Recognition2021-05-28RotNet: Fast and Scalable Estimation of Stellar Rotation Periods Using Convolutional Neural Networks2020-12-02