Interclass Prototype Relation for Few-Shot Segmentation

TL;DR

This paper introduces IPRNet, a novel few-shot segmentation method that enhances class separation by reducing interclass similarity, achieving superior performance on Pascal-5i and COCO-20i datasets.

Contribution

The paper proposes the Interclass Prototype Relation Network (IPRNet), which improves few-shot segmentation by explicitly reducing similarity between different classes.

Findings

IPRNet outperforms previous methods on Pascal-5i and COCO-20i datasets.

Reducing interclass similarity enhances segmentation accuracy.

Extensive experiments validate the effectiveness of the proposed approach.

Abstract

Traditional semantic segmentation requires a large labeled image dataset and can only be predicted within predefined classes. To solve this problem, few-shot segmentation, which requires only a handful of annotations for the new target class, is important. However, with few-shot segmentation, the target class data distribution in the feature space is sparse and has low coverage because of the slight variations in the sample data. Setting the classification boundary that properly separates the target class from other classes is an impossible task. In particular, it is difficult to classify classes that are similar to the target class near the boundary. This study proposes the Interclass Prototype Relation Network (IPRNet), which improves the separation performance by reducing the similarity between other classes. We conducted extensive experiments with Pascal-5i and COCO-20i and showed that IPRNet provides the best segmentation performance compared with previous research.