Papers › Fully Convolutional Networks for Panoptic Segmentation

Fully Convolutional Networks for Panoptic Segmentation

1 Dec 2020CVPR 2021 1arXiv:2012.00720archive 2025-07-28

Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN. Our approach aims to represent and predict foreground things and background stuff in a unified fully convolutional pipeline. In particular, Panoptic FCN encodes each object instance or stuff category into a specific kernel weight with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly. With this approach, instance-aware and semantically consistent properties for things and stuff can be respectively satisfied in a simple generate-kernel-then-segment workflow. Without extra boxes for localization or instance separation, the proposed approach outperforms previous box-based and -free models with high efficiency on COCO, Cityscapes, and Mapillary Vistas datasets with single scale input. Our code is made publicly available at https://github.com/Jia-Research-Lab/PanopticFCN.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Jia-Research-Lab/PanopticFCN officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
yanwei-li/PanopticFCN officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
DdeGeus/PanopticFCN-IBS mentioned on GitHubpytorchSyntology: not harvested report
Jia-Research-Lab/MSAD mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multi-Scale Aligned Distillation for Low-Resolution Detection (arXiv:2109.06875; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
dvlab-research/msad mentioned on GitHubpytorchSyntology: not harvested report
dvlab-research/panopticfcn mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision (arXiv:2108.07682; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Panoptic SegmentationSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) PQ 44.3 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) PQst 35.6 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) PQth 50 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) RQ 53 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) RQst 43.5 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) RQth 59.3 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) SQ 80.7 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) SQst 76.7 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (ResNet-50-FPN) SQth 83.4 #26 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) PQth 58.5 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) RQ 61.6 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) RQst 51.1 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) RQth 68.6 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) SQ 83.2 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) SQst 81.1 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO minival Panoptic FCN* (Swin-L, single-scale) SQth 84.6 #31 of 31 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FCN* (Swin-L) PQ 52.7 #10 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FCN* (Swin-L) PQth 59.4 #10 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FCN*++ (DCN-101-FPN) PQ 47.5 #21 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FCN*++ (DCN-101-FPN) PQst 38.2 #21 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev Panoptic FCN*++ (DCN-101-FPN) PQth 53.7 #21 of 38 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FCN* (ResNet-FPN) PQ 61.4 #23 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FCN* (ResNet-FPN) PQth 54.8 #23 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FCN* (Swin-L, Cityscapes-fine) PQst 70.6 #35 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FCN* (Swin-L, Cityscapes-fine) PQth 59.5 #35 of 37 Archive leaderboard report
Panoptic Segmentation Cityscapes val Panoptic FCN* (ResNet-50-FPN) PQst 66.6 #36 of 37 Archive leaderboard report
Panoptic Segmentation Mapillary val Panoptic FCN* (Swin-L, single-scale) PQ 45.7 #3 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Panoptic FCN* (Swin-L, single-scale) PQst 52.1 #3 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Panoptic FCN* (Swin-L, single-scale) PQth 40.8 #3 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Panoptic FCN* (ResNet-FPN) PQ 36.9 #10 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Panoptic FCN* (ResNet-FPN) PQth 32.9 #10 of 13 Archive leaderboard report
Panoptic Segmentation Mapillary val Panoptic FCN* (ResNet-50-FPN) PQst 42.3 #13 of 13 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

ConvolutionFCNMax Pooling

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