Advances in unsupervised learning of object-representations have culminated in the
development of a broad range of methods for unsupervised object segmentation and …

Learning structured representations of the visual world in terms of objects promises to
significantly improve the generalization abilities of current machine learning models. While …

Slot attention has shown remarkable object-centric representation learning performance in
computer vision tasks without requiring any supervision. Despite its object-centric binding …

Generic re-usable pre-trained image representation encoders have become a standard
component of methods for many computer vision tasks. As visual representations for robots …

Current visual detectors, though impressive within their training distribution, often fail to
parse out-of-distribution scenes into their constituent entities. Recent test-time adaptation …

There have recently been large advances both in pre-training visual representations for
robotic control and segmenting unknown category objects in general images. To leverage …

There have recently been large advances in the problem of segmenting unknown category
objects in general images. To leverage these for improved robot learning, we propose a new …

The locations of objects and their associated landmark keypoints can serve as versatile and
semantically meaningful image representations. In natural scenes, these keypoints are often …

We tackle the task of scalable unsupervised object-centric representation learning on 3D
scenes. Existing approaches to object-centric representation learning show limitations in …