Log In Sign Up

Bridging the Gap to Real-World Object-Centric Learning

by   Maximilian Seitzer, et al.

Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of research. However, current methods are restricted to simulated data or require additional information in the form of motion or depth in order to successfully discover objects. In this work, we overcome this limitation by showing that reconstructing features from models trained in a self-supervised manner is a sufficient training signal for object-centric representations to arise in a fully unsupervised way. Our approach, DINOSAUR, significantly out-performs existing object-centric learning models on simulated data and is the first unsupervised object-centric model that scales to real world-datasets such as COCO and PASCAL VOC. DINOSAUR is conceptually simple and shows competitive performance compared to more involved pipelines from the computer vision literature.


page 6

page 7

page 9

page 16

page 23

page 24

page 25

page 26


DAG Card is the new Model Card

With the progressive commoditization of modeling capabilities, data-cent...

Learning Explicit Object-Centric Representations with Vision Transformers

With the recent successful adaptation of transformers to the vision doma...

GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement

Advances in object-centric generative models (OCGMs) have culminated in ...

Unsupervised Image Decomposition with Phase-Correlation Networks

The ability to decompose scenes into their object components is a desire...

Complex-Valued Autoencoders for Object Discovery

Object-centric representations form the basis of human perception and en...

Object-centric Video Prediction without Annotation

In order to interact with the world, agents must be able to predict the ...

Synthetic Examples Improve Generalization for Rare Classes

The ability to detect and classify rare occurrences in images has import...