Fully Self-Supervised Class Awareness in Dense Object Descriptors

Denis Hadjivelichkov, Dimitrios Kanoulas
Proceedings of the 5th Conference on Robot Learning, PMLR 164:1522-1531, 2022.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v164-hadjivelichkov22a, title = {Fully Self-Supervised Class Awareness in Dense Object Descriptors}, author = {Hadjivelichkov, Denis and Kanoulas, Dimitrios}, booktitle = {Proceedings of the 5th Conference on Robot Learning}, pages = {1522--1531}, year = {2022}, editor = {Faust, Aleksandra and Hsu, David and Neumann, Gerhard}, volume = {164}, series = {Proceedings of Machine Learning Research}, month = {08--11 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v164/hadjivelichkov22a/hadjivelichkov22a.pdf}, url = {https://proceedings.mlr.press/v164/hadjivelichkov22a.html}, 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. } }
Endnote
%0 Conference Paper %T Fully Self-Supervised Class Awareness in Dense Object Descriptors %A Denis Hadjivelichkov %A Dimitrios Kanoulas %B Proceedings of the 5th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2022 %E Aleksandra Faust %E David Hsu %E Gerhard Neumann %F pmlr-v164-hadjivelichkov22a %I PMLR %P 1522--1531 %U https://proceedings.mlr.press/v164/hadjivelichkov22a.html %V 164 %X 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.
APA
Hadjivelichkov, D. & Kanoulas, D.. (2022). Fully Self-Supervised Class Awareness in Dense Object Descriptors. Proceedings of the 5th Conference on Robot Learning, in Proceedings of Machine Learning Research 164:1522-1531 Available from https://proceedings.mlr.press/v164/hadjivelichkov22a.html.

Related Material