Fully Self-Supervised Class Awareness in Dense Object Descriptors
Abstract
We address the problem of inferring self-supervised dense semantic correspondences between objects in multi-object scenes. The method introduces learning of class-aware dense object descriptors by providing either unsupervised discrete labels or confidence in object similarities. We quantitatively and qualitatively show that the introduced method outperforms previous techniques with more robust pixel-to-pixel matches. An example robotic application is also shown - grasping of objects in clutter based on corresponding points.
Video
Model
Our two models: DON+Hard using discrete 'hard' labels, and DON+Soft using soft confidence scores
Citation
title = {{Fully Self-Supervised Class Awareness in Dense Object Descriptors}},
author = {Hadjivelichkov, Denis and Kanoulas, Dimitrios},
journal = {Conference on Robot Learning (CoRL)},
year = {2021}
}
Authors
RPL Group, UCL
Related Work
Peter Florence*, Lucas Manuelli*, Russ Tedrake. "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation." Conference on Robot Learning (CoRL), 2018
Juntao Tan, Changkyu Song, Abdeslam Boularias. "A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs". International Conference on Robotics and Automation (ICRA). 2021
Tanner Schmidt, Richard Newcombe, Dieter Fox. "Self-supervised Visual Descriptor Learning for Dense Correspondence" Robotics and Automation Letters (RA-L), 2017