Bridging the Gap to Real-World Object-Centric Learning
This work addresses the challenge of enabling machine learning algorithms to decompose environments into entities without supervision, which is incremental as it builds on prior object-centric learning research but extends it to real-world data.
The paper tackled the problem of unsupervised object-centric learning from real-world images, overcoming previous limitations that required simulated data or additional information like motion or depth. The result was DINOSAUR, which significantly outperformed existing image-based models on simulated data and was the first to scale to real-world datasets such as COCO and PASCAL VOC.
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 image-based 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.