When the pseudo-labels are entirely incorrect, our method reduces to a training process solely using labeled data.

We consider an important problem in scientific discovery, namely identifying sparse governing equations for nonlinear dynamical systems.

An important step to understanding and improving artificial vision systems is to measure image similarity purely based on intrinsic object properties that define object identity. This problem has been studied in the computer vision literature as re-identification, though mostly restricted to specific object categories such as people and cars. We propose to extend it to general object categories, exploring an image similarity metric based on object intrinsics.

For instance, data augmentation consistency regularization [Sohn et al., 2020, Berthelot et al., 2019] generates pseudo-labels from the current model predictions on

SiamMAE operates on pairs of randomly sampled video frames and asymmetrically masks them.