GENESIS-V2: inferring unordered object representations without iterative refinement
Advances in unsupervised learning of object-representations have culminated in the development of a broad range of methods for unsupervised object segmentation and interpretable object-centric scene generation. These methods, however, are limited to simulated and real-world datasets with limited vis...
Main Authors: | Engelcke, M, Parker Jones, OP, Posner, I |
---|---|
Format: | Conference item |
Language: | English |
Published: |
Curran Associates
2022
|
Similar Items
-
GENESIS: generative scene inference and sampling of object-centric latent representations
by: Engelcke, M, et al.
Published: (2020) -
APEX: Unsupervised, object-centric scene segmentation and tracking for robot manipulation
by: Wu, Y, et al.
Published: (2021) -
Reconstruction bottlenecks in object-centric generative models
by: Engelcke, M, et al.
Published: (2020) -
Unordered Tuples in Quantum Computation
by: Robert Furber, et al.
Published: (2015-11-01) -
Deterministic Automata for Unordered Trees
by: Adrien Boiret, et al.
Published: (2014-08-01)