{"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/polymax-general-dense-prediction-with-mask","title":"PolyMaX: General Dense Prediction with Mask Transformer","arxiv_id":"2311.05770","date":"2023-11-09","proceeding":null,"authors":["Xuan Yang","Liangzhe Yuan","Kimberly Wilber","Astuti Sharma","Xiuye Gu","Siyuan Qiao","Stephanie Debats","Huisheng Wang","Hartwig Adam","Mikhail Sirotenko","Liang-Chieh Chen"],"abstract":"Dense prediction tasks, such as semantic segmentation, depth estimation, and surface normal prediction, can be easily formulated as per-pixel classification (discrete outputs) or regression (continuous outputs). This per-pixel prediction paradigm has remained popular due to the prevalence of fully convolutional networks. However, on the recent frontier of segmentation task, the community has been witnessing a shift of paradigm from per-pixel prediction to cluster-prediction with the emergence of transformer architectures, particularly the mask transformers, which directly predicts a label for a mask instead of a pixel. Despite this shift, methods based on the per-pixel prediction paradigm still dominate the benchmarks on the other dense prediction tasks that require continuous outputs, such as depth estimation and surface normal prediction. Motivated by the success of DORN and AdaBins in depth estimation, achieved by discretizing the continuous output space, we propose to generalize the cluster-prediction based method to general dense prediction tasks. This allows us to unify dense prediction tasks with the mask transformer framework. Remarkably, the resulting model PolyMaX demonstrates state-of-the-art performance on three benchmarks of NYUD-v2 dataset. We hope our simple yet effective design can inspire more research on exploiting mask transformers for more dense prediction tasks. Code and model will be made available.","url_abs":"https://arxiv.org/abs/2311.05770v1","url_pdf":"https://arxiv.org/pdf/2311.05770v1.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":"polymax-general-dense-prediction-with-mask","repo_url":"https://github.com/google-research/deeplab2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"},{"task_slug":"surface-normals-estimation","task_name":"Surface Normals Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/monocular-depth-estimation-on-nyu-depth-v2","task":"Monocular Depth Estimation","dataset":"NYU-Depth V2","model":"PolyMaX(ConvNeXt-L)","rank_in_archive_order":20,"of":85,"metrics":{"Delta < 1.25":"0.969","Delta < 1.25^2":"0.9958","Delta < 1.25^3":"0.999","RMSE":"0.25","absolute relative error":"0.067","log 10":"0.029"},"uses_additional_data":true},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"PolyMaX(ConvNeXt-L)","rank_in_archive_order":12,"of":121,"metrics":{"Mean IoU":"58.08%"},"uses_additional_data":false},{"leaderboard":"/sota/surface-normals-estimation-on-nyu-depth-v2-1","task":"Surface Normals Estimation","dataset":"NYU Depth v2","model":"PolyMaX(ConvNeXt-L)","rank_in_archive_order":2,"of":6,"metrics":{"% < 11.25":"65.66","% < 22.5":"82.28","% < 30":"87.83","Mean Angle Error":"13.09","RMSE":"20.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.05770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05770"}},"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/google-research/deeplab2","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"5e915628f1149a2f","entry":"resolve_batch_size","repo":"google-research/deeplab2","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/google-research/deeplab2/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","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":"5e915628f1149a2f"}},{"code_sha256_prefix":"e0df865e93d2e0db","entry":"scale_int_list","repo":"google-research/deeplab2","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/google-research/deeplab2/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","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":"e0df865e93d2e0db"}},{"code_sha256_prefix":"315f2fdd4f533108","entry":"scale_mutable_sequence","repo":"google-research/deeplab2","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/google-research/deeplab2/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","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":"315f2fdd4f533108"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}