Inverted-Attention Transformers can Learn Object Representations: Insights from Slot Attention

Yi-Fu Wu, Klaus Greff, Gamaleldin Fathy Elsayed, Michael Curtis Mozer, Thomas Kipf, Sjoerd van Steenkiste
January 2023
Cite OpenReview
Type
1
Publication
UniReps: the First Workshop on Unifying Representations in Neural Models