The way that information propagates in neural networks is of great
importance. In this paper, we propose Path Aggregation Network (PANet) aiming
at boosting information flow in proposal-based instance segmentation framework.
Specifically, we enhance the entire feature hierarchy with accurate
localization signals in lower layers by bottom-up path augmentation, which
shortens the information path between lower layers and topmost feature. We
present adaptive feature pooling, which links feature grid and all feature
levels to make useful information in each feature level propagate directly to
following proposal subnetworks. A complementary branch capturing different
views for each proposal is created to further improve mask prediction. These
improvements are simple to implement, with subtle extra computational overhead.
Our PANet reaches the 1st place in the COCO 2017 Challenge Instance
Segmentation task and the 2nd place in Object Detection task without
large-batch training. It is also state-of-the-art on MVD and Cityscapes. Code
is available at this https URL

本文提出 Path Aggregation Network（PANet）来提高神经网络中信息传递的效率，主要集中于基于提案的实例分割框架。具体来说，通过底层路径增强和自适应特征池化等方法来提高信息的传递效率，并建立了一个补充分支，以有效提高 Mask 预测的准确性。我们的方法在多个数据集上达到了最佳表现，具有简单易实现以及较小的计算复杂度。