# SSR-GNNs: Stroke-based Sketch Representation with Graph Neural Networks

arXiv: https://arxiv.org/abs/2204.13153 · HTML: https://mlsanity.com/paper/2204.13153/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 63 references that are in the map.
- First posted on arXiv 27 Apr 2022.

## Builds on (most cited first, 22 of 22)

- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [Sketchformer: Transformer-based Representation for Sketched Structure](https://mlsanity.com/paper/2002.10381/) (2020)
- [Deep Learning for Free-Hand Sketch: A Survey](https://mlsanity.com/paper/2001.02600/) (2020)
- [Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study](https://mlsanity.com/paper/1706.08606/) (2017)
- [SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval](https://mlsanity.com/paper/1804.01401/) (2018)
- [Multi-Graph Transformer for Free-Hand Sketch Recognition](https://mlsanity.com/paper/1912.11258/) (2019)
- [Assessing Shape Bias Property of Convolutional Neural Networks](https://mlsanity.com/paper/1803.07739/) (2018)
- [SketchGNN: Semantic Sketch Segmentation with Graph Neural Networks](https://mlsanity.com/paper/2003.00678/) (2020)
- [Fine-Grained Instance-Level Sketch-Based Video Retrieval](https://mlsanity.com/paper/2002.09461/) (2020)
- [Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognition](https://mlsanity.com/paper/1708.02716/) (2017)
- [Deep Zero-Shot Learning for Scene Sketch](https://mlsanity.com/paper/1905.04510/) (2019)

## Abstract (arXiv)

This paper follows cognitive studies to investigate a graph representation for sketches, where the information of strokes, i.e., parts of a sketch, are encoded on vertices and information of inter-stroke on edges. The resultant graph representation facilitates the training of a Graph Neural Networks for classification tasks, and achieves accuracy and robustness comparable to the state-of-the-art against translation and rotation attacks, as well as stronger attacks on graph vertices and topologies, i.e., modifications and addition of strokes, all without resorting to adversarial training. Prior studies on sketches, e.g., graph transformers, encode control points of stroke on vertices, which are not invariant to spatial transformations. In contrary, we encode vertices and edges using pairwise distances among control points to achieve invariance. Compared with existing generative sketch model for one-shot classification, our method does not rely on run-time statistical inference. Lastly, the proposed representation enables generation of novel sketches that are structurally similar to while separable from the existing dataset.