Feature Extractors

Bottom-up Path Augmentation

Introduced by Liu et al. in Path Aggregation Network for Instance Segmentation

Bottom-up Path Augmentation is a feature extraction technique that seeks to shorten the information path and enhance a feature pyramid with accurate localization signals existing in low-levels. This is based on the fact that high response to edges or instance parts is a strong indicator to accurately localize instances.

Each building block takes a higher resolution feature map $N_{i}$ and a coarser map $P_{i+1}$ through lateral connection and generates the new feature map $N_{i+1}$ Each feature map $N_{i}$ first goes through a $3 \times 3$ convolutional layer with stride $2$ to reduce the spatial size. Then each element of feature map $P_{i+1}$ and the down-sampled map are added through lateral connection. The fused feature map is then processed by another $3 \times 3$ convolutional layer to generate $N_{i+1}$ for following sub-networks. This is an iterative process and terminates after approaching $P_{5}$. In these building blocks, we consistently use channel 256 of feature maps. The feature grid for each proposal is then pooled from new feature maps, i.e., {$N_{2}$, $N_{3}$, $N_{4}$, $N_{5}$}.

Source: Path Aggregation Network for Instance Segmentation


Paper Code Results Date Stars