Log In Sign Up

Differentiable Mathematical Programming for Object-Centric Representation Learning

by   Adeel Pervez, et al.

We propose topology-aware feature partitioning into k disjoint partitions for given scene features as a method for object-centric representation learning. To this end, we propose to use minimum s-t graph cuts as a partitioning method which is represented as a linear program. The method is topologically aware since it explicitly encodes neighborhood relationships in the image graph. To solve the graph cuts our solution relies on an efficient, scalable, and differentiable quadratic programming approximation. Optimizations specific to cut problems allow us to solve the quadratic programs and compute their gradients significantly more efficiently compared with the general quadratic programming approach. Our results show that our approach is scalable and outperforms existing methods on object discovery tasks with textured scenes and objects.


page 8

page 9


Object-Centric Representation Learning with Generative Spatial-Temporal Factorization

Learning object-centric scene representations is essential for attaining...

Partitioning Graphs for the Cloud using Reinforcement Learning

In this paper, we propose Revolver, a parallel graph partitioning algori...

Language-Mediated, Object-Centric Representation Learning

We present Language-mediated, Object-centric Representation Learning (LO...

Differentiable programming: Generalization, characterization and limitations of deep learning

In the past years, deep learning models have been successfully applied i...

ILP-based Local Search for Graph Partitioning

Computing high-quality graph partitions is a challenging problem with nu...

Human-centric Image Cropping with Partition-aware and Content-preserving Features

Image cropping aims to find visually appealing crops in an image, which ...

Unsupervised Representation Learning by Discovering Reliable Image Relations

Learning robust representations that allow to reliably establish relatio...