CoChat
Sign Up
Cited by 1,460Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningVisual Attention and Saliency Detection

Panoptic Feature Pyramid Networks

Kirillov, Alexander, Girshick, Ross, He, Kaiming, Dollár, Piotr·2019·2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2019.00656
Open this paper in CoChat — free account

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 extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks. Given its effectiveness and conceptual simplicity, we hope our method can serve as a strong baseline and aid future research in panoptic segmentation.

Integrity signals

Registry

Crossref · 10.1109/cvpr.2019.00656

Cites

55 of 55 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • When using Semantic FPN for semantic segmentation on ADE20K, PVT-based models consistently outperform models based on ResNet or ResNeXt.

    “As shown in Table 5, when using Semantic FPN [32] for semantic segmentation, PVT-based models consistently outperforms the models based on ResNet [22] or ResNeXt [73].”

    From Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (2021) · cites this paper as [32]

  • A pure Transformer backbone (PVT) without convolutions can be easily plugged into dense prediction models (e.g., RetinaNet, Mask R-CNN, Semantic FPN) and obtain high-quality results.

    “These results indicate that a pure Transformer backbone ( i.e. , PVT) without convolutions can also be easily plugged in dense prediction models ( e.g. , RetinaNet [39], Mask R-CNN [21], and Semantic FPN [32]), and obtain high-quality results.”

    From Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (2021) · cites this paper as [32]

  • Learnable NMS methods and relation networks explicitly model relations between different predictions with attention.

    “Learnable NMS methods [16,4] and relation networks [17] explicitly model relations between different predictions with attention.”

    From End-to-End Object Detection with Transformers (2020) · cites this paper as [17]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Kirillov, A., Girshick, R., He, K., & Dollár, P.
Affiliations
Meta (United States) (US)
ORCID
He, Kaiming
Venue
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2019-06
Pages
6392-6401
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2019.00656
OpenAlex
W2910628332
Cited by
1,460
References
55
Citations by year
2026: 92 · 2025: 236 · 2024: 282 · 2023: 277 · 2022: 242 · 2021: 193 · 2020: 115 · 2019: 22 · 2018: 1
FWCI
46.65
Type
conference paper
Language
en
Open access
closed
Licence
Locations
IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
panoptic segmentation, instance segmentation, semantic segmentation, feature pyramid network, Mask R-CNN, shared backbone

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review