Distribution-aware Margin Calibration for Semantic Segmentation in Images

TL;DR

This paper introduces a margin calibration method for semantic segmentation that directly optimizes IoU, providing theoretical guarantees and demonstrating substantial improvements across multiple datasets.

Contribution

The paper proposes a novel margin calibration approach that directly optimizes IoU with theoretical guarantees, enhancing generalization in semantic segmentation.

Findings

Substantial IoU improvements on seven datasets.

Theoretical lower bound ensures better generalization.

Effective across various deep segmentation models.

Abstract

The Jaccard index, also known as Intersection-over-Union (IoU), is one of the most critical evaluation metrics in image semantic segmentation. However, direct optimization of IoU score is very difficult because the learning objective is neither differentiable nor decomposable. Although some algorithms have been proposed to optimize its surrogates, there is no guarantee provided for the generalization ability. In this paper, we propose a margin calibration method, which can be directly used as a learning objective, for an improved generalization of IoU over the data-distribution, underpinned by a rigid lower bound. This scheme theoretically ensures a better segmentation performance in terms of IoU score. We evaluated the effectiveness of the proposed margin calibration method on seven image datasets, showing substantial improvements in IoU score over other learning objectives using deep segmentation models.