Object-Centric Learning with Slot Mixture Models

Daniil Kirilenko, Alexey Kovalev, Aleksandr Panov

Keywords: object-centric task, gaussian mixture model, slot attention

TL;DR: We propose to use Gaussian Mixture Model to represent slots in object-centric tasks, which leads to a more expressive slots representation and the state-of-the-art results in the set property prediction task.

Abstract: Object-centric architectures usually apply some differentiable module on the whole feature map to decompose it into sets of entities representations called slots. Some of these methods structurally resemble clustering algorithms, where the center of the cluster in latent space serves as slot representation. Slot Attention is an example of such a method as a learnable analog of the soft k-Means algorithm. In our work, we use the learnable clustering method based on Gaussian Mixture Model, unlike other approaches we represent slots not only as centers of clusters but we also use information about the distance between clusters and assigned vectors, which leads to more expressive slots representations. Our experiments demonstrate that using this approach instead of Slot Attention improves performance in different scenarios achieving state-of-the-art performance in the set property prediction task.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning