Corpus ID: 219635953

Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences

@article{Weis2020UnmaskingTI,
  title={Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences},
  author={Marissa A. Weis and Kashyap Chitta and Yash Sharma and W. Brendel and M. Bethge and Andreas Geiger and Alexander S. Ecker},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.07034}
}
Perceiving the world in terms of objects is a crucial prerequisite for reasoning and scene understanding. Recently, several methods have been proposed for unsupervised learning of object-centric representations. However, since these models have been evaluated with respect to different downstream tasks, it remains unclear how they compare in terms of basic perceptual abilities such as detection, figure-ground segmentation and tracking of individual objects. In this paper, we argue that the… Expand
GATSBI: Generative Agent-centric Spatio-temporal Object Interaction
SELF-SUPERVISED VISUAL REINFORCEMENT LEARN-
  • 2020
Neural Production Systems

References

SHOWING 1-10 OF 35 REFERENCES
Multi-Object Representation Learning with Iterative Variational Inference
Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
Towards causal generative scene models via competition of experts
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks
MONet: Unsupervised Scene Decomposition and Representation
Entity Abstraction in Visual Model-Based Reinforcement Learning
...
1
2
3
4
...