We tackle the challenging task of few-shot segmentation in this work. It is essential for few-shot semantic segmentation to fully utilize the support information. Previous methods typically adopt masked average pooling over the support feature to extract the support clues as a global vector, usually dominated by the salient part and lost certain essential clues. In this work, we argue that every support pixel's information is desired to be transferred to all query pixels and propose a Correspondence Matching Network (CMNet) with an Optimal Transport Matching module to mine out the correspondence between the query and support images. Besides, it is critical to fully utilize both local and global information from the annotated support images. To this end, we propose a Message Flow module to propagate the message along the inner-flow inside the same image and cross-flow between support and query images, which greatly helps enhance the local feature representations. Experiments on PASCAL VOC 2012, MS COCO, and FSS-1000 datasets show that our network achieves new state-of-the-art few-shot segmentation performance.
翻译:在这项工作中, 我们处理的是一项具有挑战性的任务, 即使用微小的语义分割法来充分利用支持信息。 以往的方法通常会采用隐藏平均集合法, 将支持线索作为全球矢量提取出来, 通常以突出部分为主, 并丢失了某些基本线索 。 在这项工作中, 我们争辩说, 每个支持像素的信息都希望被传输到所有查询像素中, 并提议一个通信匹配网络( CMNet ), 配有一个优化的交通匹配模块, 用来清除查询和支持图像之间的对应。 此外, 充分利用本地和全球信息, 使用附加注释的支持图像至关重要 。 为此, 我们提议了一个信息流动模块, 沿同一图像内部的内流传播信息, 以及支持和查询图像之间的交叉流, 这大大有助于增强本地的特征描述 。 有关 PASAL VOC 2012 、 MS COCO 和 FSS-1000 数据集的实验显示, 我们的网络实现了新状态的微小截分段功能 。