SketchODE: Learning Neural Sketch Representation in Continuous Time

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!.

Cite

Text

Das et al. "SketchODE: Learning Neural Sketch Representation in Continuous Time." International Conference on Learning Representations, 2022.

Markdown

[Das et al. "SketchODE: Learning Neural Sketch Representation in Continuous Time." International Conference on Learning Representations, 2022.](https://mlanthology.org/iclr/2022/das2022iclr-sketchode/)

BibTeX

@inproceedings{das2022iclr-sketchode,
  title     = {{SketchODE: Learning Neural Sketch Representation in Continuous Time}},
  author    = {Das, Ayan and Yang, Yongxin and Hospedales, Timothy and Xiang, Tao and Song, Yi-Zhe},
  booktitle = {International Conference on Learning Representations},
  year      = {2022},
  url       = {https://mlanthology.org/iclr/2022/das2022iclr-sketchode/}
}