Object-Centric Learning with Slot Mixture Module
This work addresses the challenge of more expressive slot representations in object-centric learning, which is incremental over existing methods like Slot Attention.
The paper tackled the problem of object-centric representation learning by proposing a learnable clustering method based on the Gaussian Mixture Model that incorporates distance information between clusters, which improved performance in object-centric scenarios and achieved state-of-the-art results in set property prediction tasks.
Object-centric architectures usually apply a differentiable module to the entire feature map to decompose it into sets of entity representations called slots. Some of these methods structurally resemble clustering algorithms, where the cluster's center in latent space serves as a slot representation. Slot Attention is an example of such a method, acting as a learnable analog of the soft k-means algorithm. Our work employs a learnable clustering method based on the Gaussian Mixture Model. Unlike other approaches, we represent slots not only as centers of clusters but also incorporate information about the distance between clusters and assigned vectors, leading to more expressive slot representations. Our experiments demonstrate that using this approach instead of Slot Attention improves performance in object-centric scenarios, achieving state-of-the-art results in the set property prediction task.