Panoptic Feature Pyramid Networks
Alexander Kirillov, Ross Girshick, Kaiming He, Piotr Doll\'ar

TL;DR
This paper introduces Panoptic FPN, a unified, lightweight network that effectively combines instance and semantic segmentation tasks using shared computation, serving as a strong baseline for panoptic segmentation.
Contribution
The paper proposes a simple, unified architecture based on Mask R-CNN with a shared FPN backbone for both segmentation tasks, improving efficiency and performance.
Findings
Effective for both instance and semantic segmentation
Lightweight and top-performing method
Serves as a robust baseline for panoptic segmentation
Abstract
The recently introduced panoptic segmentation task has renewed our community's interest in unifying the tasks of instance segmentation (for thing classes) and semantic segmentation (for stuff classes). However, current state-of-the-art methods for this joint task use separate and dissimilar networks for instance and semantic segmentation, without performing any shared computation. In this work, we aim to unify these methods at the architectural level, designing a single network for both tasks. Our approach is to endow Mask R-CNN, a popular instance segmentation method, with a semantic segmentation branch using a shared Feature Pyramid Network (FPN) backbone. Surprisingly, this simple baseline not only remains effective for instance segmentation, but also yields a lightweight, top-performing method for semantic segmentation. In this work, we perform a detailed study of this minimally…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Domain Adaptation and Few-Shot Learning
MethodsSoftmax · Group Normalization · Random Scaling · ResNeXt Block · Grouped Convolution · ResNeXt · Panoptic FPN · Feature Pyramid Network · Average Pooling · Residual Connection
