CVDec 13, 2022

Connectivity-constrained Interactive Panoptic Segmentation

U of Toronto
arXiv:2212.06756v11 citationsh-index: 60
Originality Incremental advance
AI Analysis

This addresses annotation efficiency for computer vision researchers, but appears incremental as it builds on existing interactive segmentation methods.

The paper tackles interactive panoptic segmentation for annotating all object and stuff regions in images, proposing a framework with graph-based algorithms including a class-aware ILP formulation that ensures global optimum and connectivity, and it works with RGB or DCNN features from any dataset.

We address interactive panoptic annotation, where one segment all object and stuff regions in an image. We investigate two graph-based segmentation algorithms that both enforce connectivity of each region, with a notable class-aware Integer Linear Programming (ILP) formulation that ensures global optimum. Both algorithms can take RGB, or utilize the feature maps from any DCNN, whether trained on the target dataset or not, as input. We then propose an interactive, scribble-based annotation framework.

Foundations

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

Your Notes