Efficient Sketch Recognition Via Compact Spatial Embedding Graph Neural Networks

Hanhui Li, Xudong Jiang, Boliang Guan, Nadia Magnenat-Thalmann

Abstract

Sketches are descriptive, high-level visual media in many systems and applications. However, current methods for sketch recognition are mainly based on large neural networks, which have millions of parameters and are too cumbersome to be deployed on edge devices. Besides, convolutional neural networks are not optimal, since many areas in sketches are blank and without any information. Hence, this paper aims at designing an efficient network that maintains the state-of-the-art accuracy. Our solution is a novel graph neural network that utilizes densely connected grouped convolutions on the graph representation of sketches. It allows us to extract and aggregate spatio-temporal features efficiently. Moreover, a compact spatial embedding module is introduced to explore spatial contexts, and consequently facilitates recognition. In this way, our network is small (about 10% parameters of ResNet- 18) and efficient (inference speed in 800 ~ 2,000 FPS), meanwhile has the competitive accuracy on the QuickDraw dataset.
BibTeX
@inproceedings{li2021efficient,
  author = {Hanhui Li and Xudong Jiang and Boliang Guan and Nadia Magnenat-Thalmann},
  title = {{Efficient Sketch Recognition Via Compact Spatial Embedding Graph Neural Networks}},
  booktitle = {ICME},
  year = {2021},
  doi = {10.1109/icme51207.2021.9428180},
}

Loading related content...

Figure