In this paper, we explore the mask representation in instance segmentation
with Point-of-Interest (PoI) features. Differentiating multiple potential
instances within a single PoI feature is challenging because learning a
high-dimensional mask feature for each instance using vanilla convolution
demands a heavy computing burden. To address this challenge, we propose an
instance-aware convolution. It decomposes this mask representation learning
task into two tractable modules as instance-aware weights and instance-agnostic
features. The former is to parametrize convolution for producing mask features
corresponding to different instances, improving mask learning efficiency by
avoiding employing several independent convolutions. Meanwhile, the latter
serves as mask templates in a single point. Together, instance-aware mask
features are computed by convolving the template with dynamic weights, used for
the mask prediction. Along with instance-aware convolution, we propose
PointINS, a simple and practical instance segmentation approach, building upon
dense one-stage detectors. Through extensive experiments, we evaluated the
effectiveness of our framework built upon RetinaNet and FCOS. PointINS in
ResNet101 backbone achieves a 38.3 mask mean average precision (mAP) on COCO
dataset, outperforming existing point-based methods by a large margin. It gives
a comparable performance to the region-based Mask R-CNN with faster inference.

本文提出了一种基于 Point-of-Interest 特征的实例分割方法，将面具表示学习任务分解为实例感知权重和实例不可知特征两个可处理的模块。在 RetinaNet 和 FCOS 基础上建立的 PointINS，在 COCO 数据集上实现了 38.3 的面具平均精度（mAP），并且比现有的基于点的方法具有更高的性能。