CVJul 21, 2021

Weighted Intersection over Union (wIoU) for Evaluating Image Segmentation

arXiv:2107.09858v562 citations
Originality Synthesis-oriented
AI Analysis

This addresses the need for more flexible and intuitive evaluation metrics in the semantic segmentation field, though it appears incremental as it builds on existing IoU concepts.

The authors tackled the lack of an intuitive evaluation metric that assesses both area and boundary prediction errors in semantic segmentation by proposing weighted Intersection over Union (wIoU), which uses a weight map based on boundary distance to flexibly evaluate contour and region aspects, validated on 33 scenes.

In recent years, many semantic segmentation methods have been proposed to predict label of pixels in the scene. In general, we measure area prediction errors or boundary prediction errors for comparing methods. However, there is no intuitive evaluation metric that evaluates both aspects. In this work, we propose a new evaluation measure called weighted Intersection over Union (wIoU) for semantic segmentation. First, it builds a weight map generated from a boundary distance map, allowing weighted evaluation for each pixel based on a boundary importance factor. The proposed wIoU can evaluate both contour and region by setting a boundary importance factor. We validated the effectiveness of wIoU on a dataset of 33 scenes and demonstrated its flexibility. Using the proposed metric, we expect more flexible and intuitive evaluation in semantic segmentation field are possible.

Code Implementations1 repo
Foundations

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

Your Notes