Recent advancements in deep neural networks have made remarkable
leap-forwards in dense image prediction. However, the issue of feature
alignment remains as neglected by most existing approaches for simplicity.
Direct pixel addition between upsampled and local features leads to feature
maps with misaligned contexts that, in turn, translate to mis-classifications
in prediction, especially on object boundaries. In this paper, we propose a
feature alignment module that learns transformation offsets of pixels to
contextually align upsampled higher-level features; and another feature
selection module to emphasize the lower-level features with rich spatial
details. We then integrate these two modules in a top-down pyramidal
architecture and present the Feature-aligned Pyramid Network (FaPN). Extensive
experimental evaluations on four dense prediction tasks and four datasets have
demonstrated the efficacy of FaPN, yielding an overall improvement of 1.2 - 2.6
points in AP / mIoU over FPN when paired with Faster / Mask R-CNN. In
particular, our FaPN achieves the state-of-the-art of 56.7% mIoU on ADE20K when
integrated within Mask-Former. The code is available from
this https URL

本文提出了一种特征对齐模块和特征选择模块，用于上下文对齐上采样的高级特征，以及强调富有空间细节的低级特征，并将这两个模块集成在一个自上而下的金字塔结构中，形成了一种名为特征对齐金字塔网络（FaPN）的方法，该方法在四个密集预测任务和四个数据集上表现出比 Faster / Mask R-CNN 配对的 FPN 改进了 1.2-2.6 个 AP /mIoU 点，特别地，在 Mask-Former 中融合后，FaPN 在 ADE20K 上实现了 56.7％的 mIoU，代码可从此 URL 获得