{"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/cmt-deeplab-clustering-mask-transformers-for-1","title":"CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation","arxiv_id":"2206.08948","date":"2022-06-17","proceeding":"CVPR 2022 1","authors":["Qihang Yu","Huiyu Wang","Dahun Kim","Siyuan Qiao","Maxwell Collins","Yukun Zhu","Hartwig Adam","Alan Yuille","Liang-Chieh Chen"],"abstract":"We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer architectures used in segmentation and detection; CMT-DeepLab considers the object queries as cluster centers, which fill the role of grouping the pixels when applied to segmentation. The clustering is computed with an alternating procedure, by first assigning pixels to the clusters by their feature affinity, and then updating the cluster centers and pixel features. Together, these operations comprise the Clustering Mask Transformer (CMT) layer, which produces cross-attention that is denser and more consistent with the final segmentation task. CMT-DeepLab improves the performance over prior art significantly by 4.4% PQ, achieving a new state-of-the-art of 55.7% PQ on the COCO test-dev set.","url_abs":"https://arxiv.org/abs/2206.08948v1","url_pdf":"https://arxiv.org/pdf/2206.08948v1.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":"cmt-deeplab-clustering-mask-transformers-for-1","repo_url":"https://github.com/bytedance/kmax-deeplab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"cmt-deeplab-clustering-mask-transformers-for-1","repo_url":"https://github.com/2024-MindSpore-1/Code7/tree/main/CMT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"CMT-DeepLab (single-scale)","rank_in_archive_order":20,"of":31,"metrics":{"PQ":"55.3","PQst":"46.6","PQth":"61.0"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"CMT-DeepLab (single-scale)","rank_in_archive_order":6,"of":38,"metrics":{"PQ":"55.7","PQst":"46.8","PQth":"61.6"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"CMT-DeepLab (MaX-S, single-scale, IN-1K)","rank_in_archive_order":17,"of":37,"metrics":{"PQ":"64.6","mIoU":"81.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.08948","atlas_url":"https://app.syntology.ai/?focus=2206.08948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08948"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/2024-MindSpore-1/Code7/tree/main/CMT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bytedance/kmax-deeplab","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"listed":{"samples":8,"ran":6,"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":"fea9c1c5791db8ef","entry":"add_bias_towards_void","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/transformer_decoder/kmax_transformer_decoder.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/transformer_decoder/kmax_transformer_decoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fea9c1c5791db8ef"}},{"code_sha256_prefix":"26b60f3c795581f6","entry":"compute_class_similarity","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/matcher.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/matcher.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"26b60f3c795581f6"}},{"code_sha256_prefix":"81e3bffc1955dbf8","entry":"divide_no_nan","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/criterion.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81e3bffc1955dbf8"}},{"code_sha256_prefix":"e41d218074999206","entry":"focal_cross_entropy_loss","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/criterion.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/criterion.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e41d218074999206"}},{"code_sha256_prefix":"ccfd0fb1e16e8e61","entry":"get_activation","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/pixel_decoder/kmax_pixel_decoder.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/pixel_decoder/kmax_pixel_decoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ccfd0fb1e16e8e61"}},{"code_sha256_prefix":"21fe0f39545449df","entry":"get_norm","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/pixel_decoder/kmax_pixel_decoder.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/pixel_decoder/kmax_pixel_decoder.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21fe0f39545449df"}},{"code_sha256_prefix":"f542cee6c2318794","entry":"compute_mask_similarity","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/matcher.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/matcher.py","link_basis":"harvester_set","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":"f542cee6c2318794"}},{"code_sha256_prefix":"6c0dab27e941b121","entry":"pixelwise_insdis_loss","repo":"bytedance/kmax-deeplab","repo_kind":"listed","path":"kmax_deeplab/modeling/criterion.py","file_url":"https://github.com/bytedance/kmax-deeplab/blob/HEAD/kmax_deeplab/modeling/criterion.py","link_basis":"harvester_set","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":"6c0dab27e941b121"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}