Learning Explicit Object-Centric Representations with Vision Transformers

no code implementations • 25 Oct 2022 • Oscar Vikström, Alexander Ilin

With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features expressive for the task of object segmentation in images.

Object Segmentation +1