Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype. However, this framework suffers from biased classification due to incomplete feature comparisons. To address this issue, we present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes and thus construct complete sample pairs for learning semantic alignment with query features. The complementary features learning manner effectively enriches feature comparison and helps yield an unbiased segmentation model in the few-shot setting. It is implemented with a two-branch end-to-end network (i.e., a class-specific branch and a class-agnostic branch), which generates prototypes and then combines query features to perform comparisons. In addition, the proposed class-agnostic branch is simple yet effective. In practice, it can adaptively generate multiple class-agnostic prototypes for query images and learn feature alignment in a self-contrastive manner. Extensive experiments on PASCAL-5$^i$ and COCO-20$^i$ demonstrate the superiority of our method. At no expense of inference efficiency, our model achieves state-of-the-art results in both 1-shot and 5-shot settings for semantic segmentation.
翻译:少见的语义分解法旨在将小类对象在特定查询图像中进行分解,只有少数贴标签的支持图像。大多数先进的解决方案都利用一个衡量学习框架,通过将每个查询特征与特定类别学习的原型相匹配来进行分解。然而,这一框架由于特征比较不完整而存在偏差性分类。为了解决这一问题,我们提出了一个适应性原型代表法,引入了特定类别和类级的原型,从而构建了完整的样本配对,以学习与查询特征的语义一致。补充性特征学习方式有效地丰富了特征比较,并有助于在少数图片环境中产生一个不偏向的分化模型。它使用两个分支的端对端网络(即特定类别分支和类分级分流分支)来进行分解,产生原型,然后将查询特征合并进行比较。此外,拟议的类异性分支既简单又有效。在实践中,它能够以适应性方式生成多个类级-异性原型原型模型,用于查询图像和以自我调方式学习特征调整模式。在PASAL-5$的顶端到端网络上进行广泛的实验,以显示我们1美元的成本和CO-正位的Sat-heal-hall-xxxxxxaxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx。