Currently, the state-of-the-art methods treat few-shot semantic segmentation
task as a conditional foreground-background segmentation problem, assuming each
class is independent. In this paper, we introduce the concept of meta-class,
which is the meta information (e.g. certain middle-level features) shareable
among all classes. To explicitly learn meta-class representations in few-shot
segmentation task, we propose a novel Meta-class Memory based few-shot
segmentation method (MM-Net), where we introduce a set of learnable memory
embeddings to memorize the meta-class information during the base class
training and transfer to novel classes during the inference stage. Moreover,
for the $k$-shot scenario, we propose a novel image quality measurement module
to select images from the set of support images. A high-quality class prototype
could be obtained with the weighted sum of support image features based on the
quality measure. Experiments on both PASCAL-$5^i$ and COCO dataset shows that
our proposed method is able to achieve state-of-the-art results in both 1-shot
and 5-shot settings. Particularly, our proposed MM-Net achieves 37.5\% mIoU on
the COCO dataset in 1-shot setting, which is 5.1\% higher than the previous
state-of-the-art.

本文针对少样本语义分割任务提出一种基于元类记忆的新方法（MM-Net），引入可共享的元类概念（例如某些中间级特征），以显式地学习少样本分割任务中的元类表示，对于 $k$-shot 场景，我们还提出了图像质量测量模块来选择支持图像，最后在 PASCAL-$5^i$ 和 COCO 数据集上验证实验表明我们的方法能够在 1-shot 和 5-shot 设置下均获得最新的最好成绩。特别地，我们的 MM-Net 在 1-shot 设置下在 COCO 数据集上获得 37.5％的 mIoU 分数，比之前的最新成果高出了 5.1％。