Model Doctor for Diagnosing and Treating Segmentation Error

TL;DR

The paper introduces a Model Doctor that diagnoses and refines existing semantic segmentation models to improve accuracy and boundary precision without extra data, validated through extensive experiments.

Contribution

It presents a novel diagnostic and treatment framework for existing segmentation models, enhancing their performance without additional data.

Findings

Improved segmentation accuracy on benchmark datasets

Enhanced boundary delineation in segmentation results

Effective diagnosis and correction of model errors

Abstract

Despite the remarkable progress in semantic segmentation tasks with the advancement of deep neural networks, existing U-shaped hierarchical typical segmentation networks still suffer from local misclassification of categories and inaccurate target boundaries. In an effort to alleviate this issue, we propose a Model Doctor for semantic segmentation problems. The Model Doctor is designed to diagnose the aforementioned problems in existing pre-trained models and treat them without introducing additional data, with the goal of refining the parameters to achieve better performance. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our method. Code is available at \url{https://github.com/zhijiejia/SegDoctor}.