Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding the mixed features to a decoder. Although significant improvements have been achieved, existing methods are still face class biases due to class variants and background confusion. In this paper, we propose a joint framework that combines more valuable class-aware and class-agnostic alignment guidance to facilitate the segmentation. Specifically, we design a hybrid alignment module which establishes multi-scale query-support correspondences to mine the most relevant class-aware information for each query image from the corresponding support features. In addition, we explore utilizing base-classes knowledge to generate class-agnostic prior mask which makes a distinction between real background and foreground by highlighting all object regions, especially those of unseen classes. By jointly aggregating class-aware and class-agnostic alignment guidance, better segmentation performances are obtained on query images. Extensive experiments on PASCAL-$5^i$ and COCO-$20^i$ datasets demonstrate that our proposed joint framework performs better, especially on the 1-shot setting.
翻译:微微微分解( FSS) 旨在分割隐蔽类对象, 仅提供几个附加注释的支持图像。 多数现有方法只是通过将混杂特征添加到解码器上, 将查询功能与独立支持原型进行缝合, 并将查询图像部分部分部分与查询图像部分进行分解。 虽然已经取得了显著的改进, 但现有方法仍因等级变异和背景混乱而面临阶级偏差。 在本文件中, 我们提议了一个联合框架, 将更有价值的类认知和类认知匹配指导结合起来, 以便利分解。 具体地说, 我们设计了一个混合协调模块, 用于为来自相应支持功能的每个查询图像的相干最相关的类认知信息建立多尺度的查询支持通信。 此外, 我们探索利用基础类知识生成类前类认知掩码, 通过突出所有对象区域, 特别是隐蔽的类别, 来区分真实背景和前景。 通过将类认知和类认知调整指导联合组合, 可以在查询图像上获得更好的分解功能。 在 PACAL-5- $ 和 CO-200. 5$ 美元 数据集上进行广泛的实验。