Timezone: »

 
Oral
Provably Learning Object-Centric Representations
Jack Brady · Roland S. Zimmermann · Yash Sharma · Bernhard Schölkopf · Julius von Kügelgen · Wieland Brendel

Tue Jul 25 09:02 PM -- 09:10 PM (PDT) @ Exhibit Hall 2
in Oral A1 Causal Learning, RL, Personalization »

Learning structured representations of the visual world in terms of objects promises to significantly improve the generalization abilities of current machine learning models. While recent efforts to this end have shown promising empirical progress, a theoretical account of when unsupervised object-centric representation learning is possible is still lacking. Consequently, understanding the reasons for the success of existing object-centric methods as well as designing new theoretically grounded methods remains challenging. In the present work, we analyze when object-centric representations can provably be learned without supervision. To this end, we first introduce two assumptions on the generative process for scenes comprised of several objects, which we call compositionality and irreducibility. Under this generative process, we prove that the ground-truth object representations can be identified by an invertible and compositional inference model, even in the presence of dependencies between objects. We empirically validate our results through experiments on synthetic data. Finally, we provide evidence that our theory holds predictive power for existing object-centric models by showing a close correspondence between models' compositionality and invertibility and their empirical identifiability.

[ PDF] 

Author Information

Jack Brady (Max Planck Institute for Intelligent Systems)
Roland S. Zimmermann (University of Tübingen, MPI-IS)
Yash Sharma (University of Tübingen)
Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Bernhard Scholkopf received degrees in mathematics (London) and physics (Tubingen), and a doctorate in computer science from the Technical University Berlin. He has researched at AT&T Bell Labs, at GMD FIRST, Berlin, at the Australian National University, Canberra, and at Microsoft Research Cambridge (UK). In 2001, he was appointed scientific member of the Max Planck Society and director at the MPI for Biological Cybernetics; in 2010 he founded the Max Planck Institute for Intelligent Systems. For further information, see www.kyb.tuebingen.mpg.de/~bs.

Julius von Kügelgen (MPI for Intelligent Systems, Tübingen & University of Cambridge)
Wieland Brendel (University of Tübingen)

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

More from the Same Authors