TY  - GEN
CY  - London, UK
A1  - Hadjivelichkov, D
A1  - Kanoulas, D
T3  - Proceedings of Machine Learning Research (PMLR)
ID  - discovery10135216
N2  - 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.
UR  - https://proceedings.mlr.press/v164/hadjivelichkov22a.html
PB  - PMLR
N1  - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions.
TI  - Fully Self-Supervised Class Awareness in Dense Object Descriptors
EP  - 1531
AV  - public
Y1  - 2021/11/11/
SP  - 1522
ER  -