CVAIDec 13, 2021

Split GCN: Effective Interactive Annotation for Segmentation of Disconnected Instance

arXiv:2112.06454v16 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of high-cost human annotation for segmentation, particularly for objects with disconnected parts, offering an incremental improvement over existing interactive methods.

The paper tackles the problem of annotating disconnected object components in segmentation by introducing Split-GCN, a polygon-based method with self-attention, which achieves competitive performance with state-of-the-art models on Cityscapes and shows generalization across four cross-domain datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes