Concatenated Feature Pyramid Network for Instance Segmentation
This work addresses instance segmentation accuracy for computer vision applications, but it is incremental as it builds upon existing feature pyramid networks.
The paper tackles the problem of accurately localizing instances in neural networks by proposing an architecture that incorporates low-level features across all pyramid layers in an optimal way, resulting in consistent precision improvements on the COCO Dataset when applied to Mask RCNN.
Low level features like edges and textures play an important role in accurately localizing instances in neural networks. In this paper, we propose an architecture which improves feature pyramid networks commonly used instance segmentation networks by incorporating low level features in all layers of the pyramid in an optimal and efficient way. Specifically, we introduce a new layer which learns new correlations from feature maps of multiple feature pyramid levels holistically and enhances the semantic information of the feature pyramid to improve accuracy. Our architecture is simple to implement in instance segmentation or object detection frameworks to boost accuracy. Using this method in Mask RCNN, our model achieves consistent improvement in precision on COCO Dataset with the computational overhead compared to the original feature pyramid network.