{"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/deep-interactive-object-selection","title":"Deep Interactive Object Selection","arxiv_id":"1603.04042","date":"2016-03-13","proceeding":"CVPR 2016 6","authors":["Ning Xu","Brian Price","Scott Cohen","Jimei Yang","Thomas Huang"],"abstract":"Interactive object selection is a very important research problem and has\nmany applications. Previous algorithms require substantial user interactions to\nestimate the foreground and background distributions. In this paper, we present\na novel deep learning based algorithm which has a much better understanding of\nobjectness and thus can reduce user interactions to just a few clicks. Our\nalgorithm transforms user provided positive and negative clicks into two\nEuclidean distance maps which are then concatenated with the RGB channels of\nimages to compose (image, user interactions) pairs. We generate many of such\npairs by combining several random sampling strategies to model user click\npatterns and use them to fine tune deep Fully Convolutional Networks (FCNs).\nFinally the output probability maps of our FCN 8s model is integrated with\ngraph cut optimization to refine the boundary segments. Our model is trained on\nthe PASCAL segmentation dataset and evaluated on other datasets with different\nobject classes. Experimental results on both seen and unseen objects clearly\ndemonstrate that our algorithm has a good generalization ability and is\nsuperior to all existing interactive object selection approaches.","url_abs":"http://arxiv.org/abs/1603.04042v1","url_pdf":"http://arxiv.org/pdf/1603.04042v1.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":"deep-interactive-object-selection","repo_url":"https://github.com/IntelVCL/Intseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-interactive-object-selection","repo_url":"https://github.com/KanchanIIT/Highly-Optimized-Interactive-Image-Segmentation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-interactive-object-selection","repo_url":"https://github.com/intel-isl/Intseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"interactive-segmentation","task_name":"Interactive Segmentation"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/interactive-segmentation-on-davis","task":"Interactive Segmentation","dataset":"DAVIS","model":"DOS with GC","rank_in_archive_order":13,"of":15,"metrics":{"NoC@85":"9.03","NoC@90":"12.58"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-davis","task":"Interactive Segmentation","dataset":"DAVIS","model":"DOS w/o GC","rank_in_archive_order":14,"of":15,"metrics":{"NoC@85":"12.52","NoC@90":"17.11"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-grabcut","task":"Interactive Segmentation","dataset":"GrabCut","model":"DOS with GC","rank_in_archive_order":17,"of":18,"metrics":{"NoC@85":"5.08","NoC@90":"6.08"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-grabcut","task":"Interactive Segmentation","dataset":"GrabCut","model":"DOS w/o GC","rank_in_archive_order":18,"of":18,"metrics":{"NoC@85":"8.02","NoC@90":"12.59"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-sbd","task":"Interactive Segmentation","dataset":"SBD","model":"DOS with GC","rank_in_archive_order":11,"of":14,"metrics":{"NoC@85":"9.22","NoC@90":"12.80"},"uses_additional_data":false},{"leaderboard":"/sota/interactive-segmentation-on-sbd","task":"Interactive Segmentation","dataset":"SBD","model":"DOS w/o GC","rank_in_archive_order":12,"of":14,"metrics":{"NoC@85":"14.30","NoC@90":"16.79"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.04042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1603.04042"}},"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/KanchanIIT/Highly-Optimized-Interactive-Image-Segmentation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/IntelVCL/Intseg","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel-isl/Intseg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"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":"374548efb213f810","entry":"build_net","repo":"IntelVCL/Intseg","repo_kind":"listed","path":"IntSeg_Train.py","file_url":"https://github.com/IntelVCL/Intseg/blob/HEAD/IntSeg_Train.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":"374548efb213f810"}},{"code_sha256_prefix":"ff5b7e2b016b736e","entry":"compIoU","repo":"IntelVCL/Intseg","repo_kind":"listed","path":"our_func_cvpr18.py","file_url":"https://github.com/IntelVCL/Intseg/blob/HEAD/our_func_cvpr18.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":"ff5b7e2b016b736e"}},{"code_sha256_prefix":"f406422099514e4c","entry":"lrelu","repo":"IntelVCL/Intseg","repo_kind":"listed","path":"IntSeg_Train.py","file_url":"https://github.com/IntelVCL/Intseg/blob/HEAD/IntSeg_Train.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":"f406422099514e4c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}