{"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/benchmarking-label-noise-in-instance","title":"Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters","arxiv_id":"2406.10891","date":"2024-06-16","proceeding":null,"authors":["Eden Grad","Moshe Kimhi","Lion Halika","Chaim Baskin"],"abstract":"Obtaining accurate labels for instance segmentation is particularly challenging due to the complex nature of the task. Each image necessitates multiple annotations, encompassing not only the object's class but also its precise spatial boundaries. These requirements elevate the likelihood of errors and inconsistencies in both manual and automated annotation processes. By simulating different noise conditions, we provide a realistic scenario for assessing the robustness and generalization capabilities of instance segmentation models in different segmentation tasks, introducing COCO-N and Cityscapes-N. We also propose a benchmark for weakly annotation noise, dubbed COCO-WAN, which utilizes foundation models and weak annotations to simulate semi-automated annotation tools and their noisy labels. This study sheds light on the quality of segmentation masks produced by various models and challenges the efficacy of popular methods designed to address learning with label noise.","url_abs":"https://arxiv.org/abs/2406.10891v2","url_pdf":"https://arxiv.org/pdf/2406.10891v2.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":"benchmarking-label-noise-in-instance","repo_url":"https://github.com/eden500/Noisy-Labels-Instance-Segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"learning-with-noisy-labels","task_name":"Learning with noisy labels"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"coco-n-medium","name":"COCO-N Medium","full_name":""},{"slug":"coco-wan-medium-noise","name":"COCO-WAN (Medium noise)","full_name":"Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-coco-n-medium","task":"Instance Segmentation","dataset":"COCO-N Medium","model":"Mask R-CNN ResNet-50 FPN","rank_in_archive_order":1,"of":1,"metrics":{"mIOU":"30.3"},"uses_additional_data":false},{"leaderboard":"/sota/learning-with-noisy-labels-on-coco-wan","task":"Learning with noisy labels","dataset":"COCO-WAN","model":"Mask R-CNN (ResNet-50-FPN)","rank_in_archive_order":1,"of":1,"metrics":{"mIOU":"25.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.10891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10891"}},"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/eden500/Noisy-Labels-Instance-Segmentation","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"33116649b3da19c7","entry":"extract_bounding_box_and_area","repo":"eden500/Noisy-Labels-Instance-Segmentation","repo_kind":"official","path":"create_gt_plus_sam_noise.py","file_url":"https://github.com/eden500/Noisy-Labels-Instance-Segmentation/blob/HEAD/create_gt_plus_sam_noise.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"33116649b3da19c7"}},{"code_sha256_prefix":"6c595530d710f381","entry":"pick_noise","repo":"eden500/Noisy-Labels-Instance-Segmentation","repo_kind":"official","path":"noise_annotations.py","file_url":"https://github.com/eden500/Noisy-Labels-Instance-Segmentation/blob/HEAD/noise_annotations.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6c595530d710f381"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}