{"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/mseg-a-composite-dataset-for-multi-domain-1","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","arxiv_id":"2112.13762","date":"2021-12-27","proceeding":"CVPR 2020 6","authors":["John Lambert","Zhuang Liu","Ozan Sener","James Hays","Vladlen Koltun"],"abstract":"We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. A naive merge of the constituent datasets yields poor performance due to inconsistent taxonomies and annotation practices. We reconcile the taxonomies and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images, requiring more than 1.34 years of collective annotator effort. The resulting composite dataset enables training a single semantic segmentation model that functions effectively across domains and generalizes to datasets that were not seen during training. We adopt zero-shot cross-dataset transfer as a benchmark to systematically evaluate a model's robustness and show that MSeg training yields substantially more robust models in comparison to training on individual datasets or naive mixing of datasets without the presented contributions. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training. We evaluate our models in the 2020 Robust Vision Challenge (RVC) as an extreme generalization experiment. MSeg training sets include only three of the seven datasets in the RVC; more importantly, the evaluation taxonomy of RVC is different and more detailed. Surprisingly, our model shows competitive performance and ranks second. To evaluate how close we are to the grand aim of robust, efficient, and complete scene understanding, we go beyond semantic segmentation by training instance segmentation and panoptic segmentation models using our dataset. Moreover, we also evaluate various engineering design decisions and metrics, including resolution and computational efficiency. Although our models are far from this grand aim, our comprehensive evaluation is crucial for progress. We share all the models and code with the community.","url_abs":"https://arxiv.org/abs/2112.13762v1","url_pdf":"https://arxiv.org/pdf/2112.13762v1.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":"mseg-a-composite-dataset-for-multi-domain-1","repo_url":"https://github.com/mseg-dataset/mseg-semantic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"mseg-a-composite-dataset-for-multi-domain-1","repo_url":"https://github.com/mseg-dataset/mseg-api","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"mseg","name":"MSeg","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/semantic-segmentation-on-scannetv2","task":"Semantic Segmentation","dataset":"ScanNetV2","model":"MSeg1080_RVC","rank_in_archive_order":8,"of":12,"metrics":{"Mean IoU":"48.5%"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.13762","atlas_url":"https://app.syntology.ai/?focus=2112.13762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.13762"}},"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/mseg-dataset/mseg-semantic","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mseg-dataset/mseg-api","reach":null}],"summary":{"ran_draft_wrong":4,"ran":10,"unverified":2},"by_repo_kind":{"official":{"samples":13,"ran":11,"repositories":1},"listed":{"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":3,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/model/resnet.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/model/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"1934d9a8c4ffcd55","entry":"conv3x3","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/model/seg_hrnet.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/model/seg_hrnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1934d9a8c4ffcd55"}},{"code_sha256_prefix":"2f5a2c01a9a77336","entry":"convert_label_to_pred_taxonomy","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/relabeled_eval_utils.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/relabeled_eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f5a2c01a9a77336"}},{"code_sha256_prefix":"41d449ba30de8f98","entry":"determine_max_possible_base_size","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/universal_demo_batched.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/universal_demo_batched.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41d449ba30de8f98"}},{"code_sha256_prefix":"40602ff1d1820790","entry":"eval_rel_model_pred_on_unrel_data","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/relabeled_eval_utils.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/relabeled_eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40602ff1d1820790"}},{"code_sha256_prefix":"a4e6c6b440fcad66","entry":"get_px_accuracy","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/relabeled_eval_utils.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/relabeled_eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4e6c6b440fcad66"}},{"code_sha256_prefix":"1101e190c222d8ec","entry":"imread_rgb","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/inference_task.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/inference_task.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1101e190c222d8ec"}},{"code_sha256_prefix":"fd92a32f74219b0a","entry":"pad_to_crop_sz","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/inference_task.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/inference_task.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd92a32f74219b0a"}},{"code_sha256_prefix":"d58d1438c5b1c419","entry":"pad_to_crop_sz_batched","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/batched_inference_task.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/batched_inference_task.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d58d1438c5b1c419"}},{"code_sha256_prefix":"90a3231eeed46b30","entry":"parse_entry","repo":"mseg-dataset/mseg-api","repo_kind":"listed","path":"mseg/taxonomy/taxonomy_converter.py","file_url":"https://github.com/mseg-dataset/mseg-api/blob/HEAD/mseg/taxonomy/taxonomy_converter.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"90a3231eeed46b30"}},{"code_sha256_prefix":"1dbbfb8d6f7cad26","entry":"parse_test_entry","repo":"mseg-dataset/mseg-api","repo_kind":"listed","path":"mseg/taxonomy/taxonomy_converter.py","file_url":"https://github.com/mseg-dataset/mseg-api/blob/HEAD/mseg/taxonomy/taxonomy_converter.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1dbbfb8d6f7cad26"}},{"code_sha256_prefix":"5dcde850240a1d55","entry":"parse_uentry","repo":"mseg-dataset/mseg-api","repo_kind":"listed","path":"mseg/taxonomy/taxonomy_converter.py","file_url":"https://github.com/mseg-dataset/mseg-api/blob/HEAD/mseg/taxonomy/taxonomy_converter.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5dcde850240a1d55"}},{"code_sha256_prefix":"6ace685db42a1fe2","entry":"resize_by_scaled_short_side","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/tool/inference_task.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/tool/inference_task.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ace685db42a1fe2"}},{"code_sha256_prefix":"ac842f97bea3acce","entry":"resnet34","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/model/resnet.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/model/resnet.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ac842f97bea3acce"}},{"code_sha256_prefix":"82fc6d977d54d3df","entry":"exclusion","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/utils/avg_meter.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/utils/avg_meter.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82fc6d977d54d3df"}},{"code_sha256_prefix":"0bde1125893e0d96","entry":"resnet18","repo":"mseg-dataset/mseg-semantic","repo_kind":"official","path":"mseg_semantic/model/resnet.py","file_url":"https://github.com/mseg-dataset/mseg-semantic/blob/HEAD/mseg_semantic/model/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0bde1125893e0d96"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}