3 citations · 3 across the 4 of their papers we have counts for
4 papers
Cycle-Correspondence Loss: Learning Dense View-Invariant Visual Features from Unlabeled and Unordered RGB Images
David B. Adrian, Andras Gabor Kupcsik, Markus Spies +1
Robot manipulation relying on learned object-centric descriptors became popular in recent years. Visual descriptors can easily describe manipulation task objectives, they can be le…
Learning Dense Visual Descriptors using Image Augmentations for Robot Manipulation Tasks
Christian Graf, David B. Adrian, Joshua Weil +5
We propose a self-supervised training approach for learning view-invariant dense visual descriptors using image augmentations. Unlike existing works, which often require complex da…
Efficient and Robust Training of Dense Object Nets for Multi-Object Robot Manipulation
David B. Adrian, Andras Gabor Kupcsik, Markus Spies +1
We propose a framework for robust and efficient training of Dense Object Nets (DON) with a focus on multi-object robot manipulation scenarios. DON is a popular approach to obtain d…
Weakly supervised collective feature learning from curated media
Yusuke Mukuta, Akisato Kimura, David B Adrian +1
The current state-of-the-art in feature learning relies on the supervised learning of large-scale datasets consisting of target content items and their respective category labels.…