# Split GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance

arXiv: https://arxiv.org/abs/2112.06454 · HTML: https://mlsanity.com/paper/2112.06454/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 53 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs](https://mlsanity.com/paper/1412.7062/) (2014)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [Deep Interactive Object Selection](https://mlsanity.com/paper/1603.04042/) (2016)
- [Deep Extreme Cut: From Extreme Points to Object Segmentation](https://mlsanity.com/paper/1711.09081/) (2017)
- [Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++](https://mlsanity.com/paper/1803.09693/) (2018)
- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Fast Interactive Object Annotation with Curve-GCN](https://mlsanity.com/paper/1903.06874/) (2019)
- [PolyTransform: Deep Polygon Transformer for Instance Segmentation](https://mlsanity.com/paper/1912.02801/) (2019)
- [Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth](https://mlsanity.com/paper/1906.11109/) (2019)
- [Annotating Object Instances with a Polygon-RNN](https://mlsanity.com/paper/1704.05548/) (2017)
- [SSAP: Single-Shot Instance Segmentation With Affinity Pyramid](https://mlsanity.com/paper/1909.01616/) (2019)
- [Extreme clicking for efficient object annotation](https://mlsanity.com/paper/1708.02750/) (2017)
- [Deep Watershed Transform for Instance Segmentation](https://mlsanity.com/paper/1611.08303/) (2016)
- [AdaptIS: Adaptive Instance Selection Network](https://mlsanity.com/paper/1909.07829/) (2019)
- [Iteratively Trained Interactive Segmentation](https://mlsanity.com/paper/1805.04398/) (2018)
- [Learning deep structured active contours end-to-end](https://mlsanity.com/paper/1803.06329/) (2018)
- [Affinity Derivation and Graph Merge for Instance Segmentation](https://mlsanity.com/paper/1811.10870/) (2018)
- [Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid](https://mlsanity.com/paper/2008.09269/) (2020)

## Built on by (most cited first, 2 of 2)

- [VSR-Net: Vessel-like Structure Rehabilitation Network with Graph Clustering](https://mlsanity.com/paper/2312.13116/) (2023)
- [Interactive Instance Annotation with Siamese Networks](https://mlsanity.com/paper/2505.03184/) (2025)

## Abstract (arXiv)

Annotating object boundaries by humans demands high costs. Recently, polygon-based annotation methods with human interaction have shown successful performance. However, given the connected vertex topology, these methods exhibit difficulty predicting the disconnected components in an object. This paper introduces Split-GCN, a novel architecture based on the polygon approach and self-attention mechanism. By offering the direction information, Split-GCN enables the polygon vertices to move more precisely to the object boundary. Our model successfully predicts disconnected components of an object by transforming the initial topology using the context exchange about the dependencies of vertices. Split-GCN demonstrates competitive performance with the state-of-the-art models on Cityscapes and even higher performance with the baseline models. On four cross-domain datasets, we confirm our model's generalization ability.