{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/k-net-towards-unified-image-segmentation","title":"K-Net: Towards Unified Image Segmentation","arxiv_id":"2106.14855","date":"2021-06-28","proceeding":"NeurIPS 2021 12","authors":["Wenwei Zhang","Jiangmiao Pang","Kai Chen","Chen Change Loy"],"abstract":"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/.","url_abs":"https://arxiv.org/abs/2106.14855v2","url_pdf":"https://arxiv.org/pdf/2106.14855v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"k-net-towards-unified-image-segmentation","repo_url":"https://github.com/zwwwayne/k-net","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"cascade-mask-r-cnn","method_name":"Cascade Mask R-CNN"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"k-net","method_name":"K-Net"},{"method_slug":"mask-r-cnn","method_name":"Mask R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"roi-align","method_name":"RoIAlign"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[{"slug":"k-net","name":"K-Net","full_name":"K-Net"}],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"K-Net-N256 (ResNet-101)","rank_in_archive_order":67,"of":112,"metrics":{"AP50":"63.3","APL":"59","APM":"43.3","APS":"18.8","mask AP":"40.6%"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"K-Net (ResNet-101)","rank_in_archive_order":72,"of":112,"metrics":{"AP50":"62.8","APL":"58.8","APM":"42.7","APS":"18.7","mask AP":"40.1%"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"K-Net (Swin-L)","rank_in_archive_order":7,"of":38,"metrics":{"PQ":"55.2","PQst":"46.2","PQth":"61.2"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"K-Net (R101-FPN-DCN)","rank_in_archive_order":19,"of":38,"metrics":{"PQ":"48.3","PQst":"39.7","PQth":"54"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k","task":"Semantic Segmentation","dataset":"ADE20K","model":"K-Net","rank_in_archive_order":63,"of":235,"metrics":{"Validation mIoU":"54.3"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"K-Net","rank_in_archive_order":33,"of":95,"metrics":{"mIoU":"54.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.14855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14855"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zwwwayne/k-net","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ab4462f156c6ae4f","entry":"sem2ins_masks","repo":"zwwwayne/k-net","repo_kind":"official","path":"knet/det/utils.py","file_url":"https://github.com/zwwwayne/k-net/blob/HEAD/knet/det/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ab4462f156c6ae4f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}