Papers › K-Net: Towards Unified Image Segmentation

K-Net: Towards Unified Image Segmentation

28 Jun 2021NeurIPS 2021 12arXiv:2106.14855archive 2025-07-28

Wenwei Zhang, Jiangmiao Pang, Kai Chen, Chen Change Loy

Semantic, instance, and panoptic segmentations have been addressed using different and specialized frameworks despite their underlying connections. This paper presents a unified, simple, and effective framework for these essentially similar tasks. The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels, where each kernel is responsible for generating a mask for either a potential instance or a stuff class. To remedy the difficulties of distinguishing various instances, we propose a kernel update strategy that enables each kernel dynamic and conditional on its meaningful group in the input image. K-Net can be trained in an end-to-end manner with bipartite matching, and its training and inference are naturally NMS-free and box-free. Without bells and whistles, K-Net surpasses all previous published state-of-the-art single-model results of panoptic segmentation on MS COCO test-dev split and semantic segmentation on ADE20K val split with 55.2% PQ and 54.3% mIoU, respectively. Its instance segmentation performance is also on par with Cascade Mask R-CNN on MS COCO with 60%-90% faster inference speeds. Code and models will be released at https://github.com/ZwwWayne/K-Net/.

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="2106.14855")

Code

Syntology Ran 0 of 1 code samples harvested from 1 repository linked to this paper; 1 has no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zwwwayne/k-net officialmentioned in papermentioned on GitHubpytorchApache-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

1 sample harvested; 0 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1unverified

Licence: 0 of the 1 sample 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 zwwwayne/k-net. “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.

sem2ins_masks zwwwayne/k-net/knet/det/utils.py official repository unverified Apache-2.0 (permissive) · ab4462f156c6ae4f · report

Tasks

Image SegmentationInstance SegmentationPanoptic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO test-dev K-Net-N256 (ResNet-101) AP50 63.3 #67 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net-N256 (ResNet-101) APL 59 #67 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net-N256 (ResNet-101) APM 43.3 #67 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net-N256 (ResNet-101) APS 18.8 #67 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net-N256 (ResNet-101) mask AP 40.6% #67 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net (ResNet-101) AP50 62.8 #72 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net (ResNet-101) APL 58.8 #72 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net (ResNet-101) APM 42.7 #72 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net (ResNet-101) APS 18.7 #72 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev K-Net (ResNet-101) mask AP 40.1% #72 of 112 Archive leaderboard report
Panoptic Segmentation COCO test-dev K-Net (Swin-L) PQ 55.2 #7 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev K-Net (Swin-L) PQst 46.2 #7 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev K-Net (Swin-L) PQth 61.2 #7 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev K-Net (R101-FPN-DCN) PQ 48.3 #19 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev K-Net (R101-FPN-DCN) PQst 39.7 #19 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev K-Net (R101-FPN-DCN) PQth 54 #19 of 38 Archive leaderboard report
Semantic Segmentation ADE20K K-Net Validation mIoU 54.3 #63 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val K-Net mIoU 54.3 #33 of 95 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: K-Net

Cascade Mask R-CNNConvolutionK-NetMask R-CNNRPNRoIAlignSoftmax

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