Fully Self-Supervised Class Awareness in Dense Object Descriptors
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Oct 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2022: 3; 2023: 1; 2024: 1.
5 papers.
- 2022One-Shot Transfer of Affordance Regions? AffCorrs!cited by 31
- 2023The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulationcited by 12
- 2022Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalizationcited by 6
- 2022Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulationcited by 3
- 2024Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Imagescited by 1
- 2024Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images18 Jun 2024
- 2023The Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation8 May 2023
- 2022Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalization28 Nov 2022
- 2022One-Shot Transfer of Affordance Regions? AffCorrs!15 Sep 2022
- 2022Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation17 May 2022