SCIENCE@home

Entropy-driven Unsupervised Keypoint Representation Learning in Videos

A. Younes,Simone Schaub-Meyer,Georgia Chalvatzaki

Published 2022 in International Conference on Machine Learning

ABSTRACT

Extracting informative representations from videos is fundamental for effectively learning various downstream tasks. We present a novel approach for unsupervised learning of meaningful representations from videos, leveraging the concept of image spatial entropy (ISE) that quantifies the per-pixel information in an image. We argue that \textit{local entropy} of pixel neighborhoods and their temporal evolution create valuable intrinsic supervisory signals for learning prominent features. Building on this idea, we abstract visual features into a concise representation of keypoints that act as dynamic information transmitters, and design a deep learning model that learns, purely unsupervised, spatially and temporally consistent representations \textit{directly} from video frames. Two original information-theoretic losses, computed from local entropy, guide our model to discover consistent keypoint representations; a loss that maximizes the spatial information covered by the keypoints and a loss that optimizes the keypoints' information transportation over time. We compare our keypoint representation to strong baselines for various downstream tasks, \eg, learning object dynamics. Our empirical results show superior performance for our information-driven keypoints that resolve challenges like attendance to static and dynamic objects or objects abruptly entering and leaving the scene.

PUBLICATION RECORD

  • Publication year

    2022

  • Venue

    International Conference on Machine Learning

  • Publication date

    2022-09-30

  • Fields of study

    Computer Science

  • Identifiers
    arXiv 2209.15404
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-94 of 94 references · Page 1 of 1

CITED BY