Papers › Panoptic Feature Pyramid Networks

Panoptic Feature Pyramid Networks

8 Jan 2019CVPR 2019 6arXiv:1901.02446archive 2025-07-28

Alexander Kirillov, Ross Girshick, Kaiming He, Piotr Dollár

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1901.02446")

Code

Syntology Ran 7 of 12 code samples harvested from 2 repositories linked to this paper; 5 have no recorded run. Of those that ran: 6 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 12 samples from 2 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Shun14/panopticFPN-paddle mentioned on GitHubpaddleApache-2.0 report
Vishal-V/tf-models mentioned on GitHubtfMIT report
ashwath007/amenity-detection mentioned on GitHubpytorchApache-2.0 report
ashwath007/aminity-detection mentioned on GitHubpytorchApache-2.0 report
dajes/DensePose-TorchScript mentioned on GitHubpytorch report
jlazarow/learning_instance_occlusion mentioned on GitHubpytorch report
open-mmlab/mmdetection pytorchApache-2.0 report
open-mmlab/mmsegmentation pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 7 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

6ran · our draft was wrong
1ran · fixture could not drive it
5unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

add_extras ashwath007/amenity-detection/Algo/SSD/ssd.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 2a8545e480332b47 · report
get_test_config Shun14/panopticFPN-paddle/val.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 20eb3e6b0aba73e4 · report
intersect ashwath007/amenity-detection/Algo/SSD/layers/box_utils.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · f01c5f73515770a5 · report
multibox ashwath007/amenity-detection/Algo/SSD/ssd.py community (archive-listed) ran · fixture could not drive it Apache-2.0 (permissive) · 40dc7296d52276ff · report
partition_list Shun14/panopticFPN-paddle/paddleseg/core/predict.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 2f75a098ce9f7b0e · report
point_form ashwath007/amenity-detection/Algo/SSD/layers/box_utils.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3bea1addc1e14162 · report
vgg ashwath007/amenity-detection/Algo/SSD/ssd.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 6921f7ed00595a4f · report
center_size ashwath007/amenity-detection/Algo/SSD/layers/box_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · aa1d78402838820a · report
flip_combination Shun14/panopticFPN-paddle/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 95bccf5957a196e4 · report
get_image_list Shun14/panopticFPN-paddle/predict.py community (archive-listed) unverified Apache-2.0 (permissive) · c8f710d7401e0006 · report
get_reverse_list Shun14/panopticFPN-paddle/paddleseg/core/infer.py community (archive-listed) unverified Apache-2.0 (permissive) · 026fee631ce4a66c · report
get_test_config Shun14/panopticFPN-paddle/predict.py community (archive-listed) unverified Apache-2.0 (permissive) · 32d2a7cc8725e25e · report

Tasks

Instance SegmentationPanoptic SegmentationSegmentationSemantic SegmentationThermal Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation COCO test-dev Panoptic FPN PQ 40.9 #32 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FPN PQst 29.7 #32 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FPN PQth 48.3 #32 of 38 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FPN (ResNet-101) AP 33.0 #32 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FPN (ResNet-101) PQ 58.1 #32 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FPN (ResNet-101) PQst 62.5 #32 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FPN (ResNet-101) PQth 52.0 #32 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FPN (ResNet-101) mIoU 75.7 #32 of 37 Archive leaderboard report
Panoptic Segmentation Indian Driving Dataset Panoptic FPN PQ 46.7 #4 of 4 Archive leaderboard report
Panoptic Segmentation KITTI Panoptic Segmentation Panoptic FPN PQ 39.3 #4 of 4 Archive leaderboard report
Semantic Segmentation DADA-seg Semantic FPN (ResNet-101) mIoU 19.59 #23 of 28 Archive leaderboard report
Semantic Segmentation DensePASS Semantic-FPN (ResNet-101) mIoU 28.8% #29 of 36 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Panoptic FPN

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNGlobal Average PoolingGroup NormalizationGrouped ConvolutionKaiming InitializationMax PoolingPanoptic FPNRandom ScalingReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections