Search Results for author:
Found 2 papers, 1 papers with code
Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
Understanding which inductive biases could be helpful for the unsupervised learning of object-centric representations of natural scenes is challenging.
Generalization and Robustness Implications in Object-Centric Learning
The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
