supervised adptive threshold network for instance segmentation

TL;DR

This paper introduces a supervised adaptive threshold network that enhances instance segmentation by improving information propagation and segmentation accuracy through adaptive binarization and feature pooling.

Contribution

It proposes a novel adaptive threshold mechanism and layered structure to improve segmentation accuracy over traditional Mask R-CNN models.

Findings

Improved segmentation accuracy on benchmark datasets.

Reduced error rate in instance segmentation.

Enhanced feature transmission between network layers.

Abstract

Currently, instance segmentation is attracting more and more attention in machine learning region. However, there exists some defects on the information propagation in previous Mask R-CNN and other network models. In this paper, we propose supervised adaptive threshold network for instance segmentation. Specifically, we adopt the Mask R-CNN method based on adaptive threshold, and by establishing a layered adaptive network structure, it performs adaptive binarization on the probability graph generated by Mask RCNN to obtain better segmentation effect and reduce the error rate. At the same time, an adaptive feature pool is designed to make the transmission between different layers of the network more accurate and effective, reduce the loss in the process of feature transmission, and further improve the mask method. Experiments on benchmark data sets indicate that the effectiveness of the proposed model