Whitening for Self-Supervised Representation Learning

           Aleksandr Ermolov 1 Aliaksandr Siarohin 1 Enver Sangineto 1 Nicu Sebe 1

             Abstract                 of words in a sentence is used to learn a language model
                                  (Mikolov et al., 2013a;b; Devlin et al., 2019). In Computer
   Most of the current self-supervised representation       Vision, typical contexts or pretext tasks are based on: (1)
   learning (SSL) methods are based on the con-      ...