{"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/cfr-icl-cascade-forward-refinement-with","title":"CFR-ICL: Cascade-Forward Refinement with Iterative Click Loss for Interactive Image Segmentation","arxiv_id":"2303.05620","date":"2023-03-09","proceeding":null,"authors":["Shoukun Sun","Min Xian","Fei Xu","Luca Capriotti","Tiankai Yao"],"abstract":"The click-based interactive segmentation aims to extract the object of interest from an image with the guidance of user clicks. Recent work has achieved great overall performance by employing feedback from the output. However, in most state-of-the-art approaches, 1) the inference stage involves inflexible heuristic rules and requires a separate refinement model, and 2) the number of user clicks and model performance cannot be balanced. To address the challenges, we propose a click-based and mask-guided interactive image segmentation framework containing three novel components: Cascade-Forward Refinement (CFR), Iterative Click Loss (ICL), and SUEM image augmentation. The CFR offers a unified inference framework to generate segmentation results in a coarse-to-fine manner. The proposed ICL allows model training to improve segmentation and reduce user interactions simultaneously. The proposed SUEM augmentation is a comprehensive way to create large and diverse training sets for interactive image segmentation. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach on five public datasets. Remarkably, our model reduces by 33.2\\%, and 15.5\\% the number of clicks required to surpass an IoU of 0.95 in the previous state-of-the-art approach on the Berkeley and DAVIS sets, respectively.","url_abs":"https://arxiv.org/abs/2303.05620v2","url_pdf":"https://arxiv.org/pdf/2303.05620v2.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":"cfr-icl-cascade-forward-refinement-with","repo_url":"https://github.com/TitorX/CFR-ICL-Interactive-Segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-augmentation","task_name":"Image Augmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"interactive-segmentation","task_name":"Interactive Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/interactive-segmentation-on-berkeley","task":"Interactive Segmentation","dataset":"Berkeley","model":"ICL CFR-1 (ViT-H, C+L)","rank_in_archive_order":1,"of":14,"metrics":{"NoC@90":"1.46","NoC@95":"2.90"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-davis","task":"Interactive Segmentation","dataset":"DAVIS","model":"ICL CFR-1 (ViT-H, C+L)","rank_in_archive_order":1,"of":15,"metrics":{"NoC@85":"3","NoC@90":"4.24","NoC@95":"7.50"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-grabcut","task":"Interactive Segmentation","dataset":"GrabCut","model":"SimpleClick CFR-1 (ViT-H, SBD)","rank_in_archive_order":1,"of":18,"metrics":{"NoC@85":"1.30","NoC@90":"1.32","NoC@95":"1.78"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-grabcut","task":"Interactive Segmentation","dataset":"GrabCut","model":"ICL CFR-1 (ViT-H, SBD)","rank_in_archive_order":3,"of":18,"metrics":{"NoC@90":"1.42","NoC@95":"1.62"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-pascal-voc","task":"Interactive Segmentation","dataset":"PASCAL VOC","model":"ICL CFR-1 (ViT-H, C+L)","rank_in_archive_order":1,"of":2,"metrics":{"NoC@85":"1.72","NoC@90":"1.94","NoC@95":"2.45"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-sbd","task":"Interactive Segmentation","dataset":"SBD","model":"SimpleClick CFR-1 (ViT-H, SBD)","rank_in_archive_order":1,"of":14,"metrics":{"NoC@85":"2.45","NoC@90":"4.08","NoC@95":"9.80"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.05620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.05620"}},"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/TitorX/CFR-ICL-Interactive-Segmentation","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"98528abf8b3bbe19","entry":"get_predictor_and_zoomin_params","repo":"TitorX/CFR-ICL-Interactive-Segmentation","repo_kind":"official","path":"scripts/evaluate_model.py","file_url":"https://github.com/TitorX/CFR-ICL-Interactive-Segmentation/blob/HEAD/scripts/evaluate_model.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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"98528abf8b3bbe19"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}