Corpus ID: 219708374

Learning About Objects by Learning to Interact with Them

@article{Lohmann2020LearningAO,
  title={Learning About Objects by Learning to Interact with Them},
  author={M. Lohmann and J. Salvador and Aniruddha Kembhavi and R. Mottaghi},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.09306}
}
  • M. Lohmann, J. Salvador, +1 author R. Mottaghi
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often learn about their world with little to no external supervision. Taking inspiration from infants learning from their environment through play and interaction, we present a computational framework to discover objects and learn their physical properties along this paradigm of Learning from Interaction… CONTINUE READING
    1 Citations

    Figures and Tables from this paper.

    AllenAct: A Framework for Embodied AI Research
    • 3
    • PDF

    References

    SHOWING 1-10 OF 64 REFERENCES
    Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction
    • 4
    • PDF
    AI2-THOR: An Interactive 3D Environment for Visual AI
    • 203
    • PDF
    Attend, Infer, Repeat: Fast Scene Understanding with Generative Models
    • 247
    • PDF
    Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments
    • 62
    • PDF
    Towards Computational Baby Learning: A Weakly-Supervised Approach for Object Detection
    • 83
    • PDF
    Visual Reaction: Learning to Play Catch With Your Drone
    • 2
    • PDF
    Scaling and Benchmarking Self-Supervised Visual Representation Learning
    • 89
    • PDF
    Looking Beyond the Image: Unsupervised Learning for Object Saliency and Detection
    • 149
    • PDF
    Watch and learn: Semi-supervised learning of object detectors from videos
    • 93
    • PDF