Corpus ID: 212414722

SCALOR: Generative World Models with Scalable Object Representations

@inproceedings{Jiang2020SCALORGW,
  title={SCALOR: Generative World Models with Scalable Object Representations},
  author={Jindong Jiang and Sepehr Janghorbani and Gerard de Melo and Sungjin Ahn},
  booktitle={ICLR},
  year={2020}
}
  • Jindong Jiang, Sepehr Janghorbani, +1 author Sungjin Ahn
  • Published in ICLR 2020
  • Computer Science, Mathematics
  • Scalability in terms of object density in a scene is a primary challenge in unsupervised sequential object-oriented representation learning. Most of the previous models have been shown to work only on scenes with a few objects. In this paper, we propose SCALOR, a probabilistic generative world model for learning SCALable Object-oriented Representation of a video. With the proposed spatially parallel attention and proposal-rejection mechanisms, SCALOR can deal with orders of magnitude larger… CONTINUE READING
    12 Citations
    Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences
    Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking
    • 10
    • PDF
    Learning to Infer 3D Object Models from Images
    • 1
    Object-Centric Learning with Slot Attention
    • 8
    • PDF
    Unsupervised object-centric video generation and decomposition in 3D
    Slot Contrastive Networks: A Contrastive Approach for Representing Objects
    • 1
    • PDF
    Generative Neurosymbolic Machines
    Hierarchical Relational Inference
    Reconstruction Bottlenecks in Object-Centric Generative Models

    References

    SHOWING 1-10 OF 26 REFERENCES
    SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
    • 18
    • PDF
    Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
    • 246
    • Highly Influential
    • PDF
    GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
    • 34
    • PDF
    Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking
    • 10
    • PDF
    MONet: Unsupervised Scene Decomposition and Representation
    • 89
    • PDF
    Hierarchical Attentive Recurrent Tracking
    • 44
    • PDF
    Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objects
    • 74
    • PDF
    Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackers
    • 16
    • Highly Influential
    • PDF