SketchODE: Learning neural sketch representation in continuous time

International Conference on Learning Representations (ICLR), 2022
Generative Models
Differential Equations
Sketches
Authors
Affiliations

Ayan Das

SketchX, CVSSP, University of Surrey

Yongxin Yang

Queen Mary University of London, UK

Timothy Hospedales

University of Edinburgh, UK

Samsung AI Center, Cambridge

Tao Xiang

SketchX, CVSSP, University of Surrey

Yi-Zhe Song

SketchX, CVSSP, University of Surrey

Published

January 21, 2022

Paper Code

Abstract

Learning meaningful representations for chirographic drawing data such as sketches, handwriting, and flowcharts is a gateway for understanding and emulating human creative expression. Despite being inherently continuous-time data, existing works have treated these as discrete-time sequences, disregarding their true nature. In this work, we model such data as continuous-time functions and learn compact representations by virtue of Neural Ordinary Differential Equations. To this end, we introduce the first continuous-time Seq2Seq model and demonstrate some remarkable properties that set it apart from traditional discrete-time analogues. We also provide solutions for some practical challenges for such models, including introducing a family of parameterized ODE dynamics & continuous-time data augmentation particularly suitable for the task. Our models are validated on several datasets including VectorMNIST, DiDi and Quick, Draw!.

Citation

BibTeX citation:
@inproceedings{das2022,
  author = {Das, Ayan and Yang, Yongxin and Hospedales, Timothy and
    Xiang, Tao and Song, Yi-Zhe},
  title = {SketchODE: {Learning} Neural Sketch Representation in
    Continuous Time},
  booktitle = {International Conference on Learning Representations
    (ICLR), 2022},
  date = {2022-01-21},
  url = {https://openreview.net/pdf?id=c-4HSDAWua5},
  langid = {en}
}
For attribution, please cite this work as:
Das, Ayan, Yongxin Yang, Timothy Hospedales, Tao Xiang, and Yi-Zhe Song. 2022. “SketchODE: Learning Neural Sketch Representation in Continuous Time.” In International Conference on Learning Representations (ICLR), 2022. https://openreview.net/pdf?id=c-4HSDAWua5.