Timezone: »

Object-Centric Learning with Slot Attention
Francesco Locatello · Dirk Weissenborn · Thomas Unterthiner · Aravindh Mahendran · Georg Heigold · Jakob Uszkoreit · Alexey Dosovitskiy · Thomas Kipf

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1405

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not capture the compositional properties of natural scenes. In this paper, we present the Slot Attention module, an architectural component that interfaces with perceptual representations such as the output of a convolutional neural network and produces a set of task-dependent abstract representations which we call slots. These slots are exchangeable and can bind to any object in the input by specializing through a competitive procedure over multiple rounds of attention. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions when trained on unsupervised object discovery and supervised property prediction tasks.

Author Information

Francesco Locatello (ETH Zürich - MPI Tübingen)
Dirk Weissenborn (Google)
Thomas Unterthiner (Google Research, Brain Team)
Aravindh Mahendran (Google)
Georg Heigold (Google)
Jakob Uszkoreit (Google, Inc.)
Alexey Dosovitskiy (Google Research)
Thomas Kipf (Google Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors