MFP: Making Full Use of Probability Maps for Interactive Image Segmentation

TL;DR

The paper introduces MFP, a novel algorithm that enhances interactive image segmentation by fully utilizing probability maps, leading to improved performance across various datasets.

Contribution

MFP modulates and integrates probability maps into segmentation networks, significantly improving interactive segmentation accuracy over existing methods.

Findings

MFP outperforms existing algorithms with the same backbones.

The method is effective across multiple datasets.

Source code is publicly available for reproducibility.

Abstract

In recent interactive segmentation algorithms, previous probability maps are used as network input to help predictions in the current segmentation round. However, despite the utilization of previous masks, useful information contained in the probability maps is not well propagated to the current predictions. In this paper, to overcome this limitation, we propose a novel and effective algorithm for click-based interactive image segmentation, called MFP, which attempts to make full use of probability maps. We first modulate previous probability maps to enhance their representations of user-specified objects. Then, we feed the modulated probability maps as additional input to the segmentation network. We implement the proposed MFP algorithm based on the ResNet-34, HRNet-18, and ViT-B backbones and assess the performance extensively on various datasets. It is demonstrated that MFP meaningfully outperforms the existing algorithms using identical backbones. The source codes are available at https://github.com/cwlee00/MFP.