Few-shot semantic segmentation aims at recognizing the object regions of unseen categories with only a few annotated examples as supervision. The key to few-shot segmentation is to establish a robust semantic relationship between the support and query images and to prevent overfitting. In this paper, we propose an effective Multi-similarity Hyperrelation Network (MSHNet) to tackle the few-shot semantic segmentation problem. In MSHNet, we propose a new Generative Prototype Similarity (GPS), which together with cosine similarity can establish a strong semantic relation between the support and query images. The locally generated prototype similarity based on global feature is logically complementary to the global cosine similarity based on local feature, and the relationship between the query image and the supported image can be expressed more comprehensively by using the two similarities simultaneously. In addition, we propose a Symmetric Merging Block (SMB) in MSHNet to efficiently merge multi-layer, multi-shot and multi-similarity hyperrelational features. MSHNet is built on the basis of similarity rather than specific category features, which can achieve more general unity and effectively reduce overfitting. On two benchmark semantic segmentation datasets Pascal-5i and COCO-20i, MSHNet achieves new state-of-the-art performances on 1-shot and 5-shot semantic segmentation tasks.
翻译:少见的语义分割法旨在识别看不见类别的目标区域,只有几个附加说明的例子作为监督。 少见部分分割法的关键在于建立支持和查询图像之间牢固的语义关系,防止过度配配。 在本文中,我们建议建立一个有效的多样超异关系网络(MSHNet)来解决微粒语义分割法问题。 在 MSHNet 中, 我们提议一个新的“ 产生性质样相似性( GPS) ” (GPS), 与 共性相似性( GPS) 一起可以在支持和查询图像之间建立强烈的语义关系。 以全球特征为基础的本地生成的原型相似性在逻辑上可以补充基于本地特征的全球共性, 查询图像与所支持的图像之间的关系可以通过同时使用两个相似性来更全面地表达。 此外, 我们提议在 MSHNet 中建立一个共性合并区块(SMB), 以高效地将多层、多光谱和多相似性极性高性关系特征结合起来。 MSHNet 建基于相似性而不是特定类别特性, 在两个类别特性的基础上建起, 能够实现总体统一和SMSHASASAL 5 常规分级新的数据分级, 。