{"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/learning-to-generate-text-grounded-mask-for","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","arxiv_id":"2212.00785","date":"2022-12-01","proceeding":"CVPR 2023 1","authors":["Junbum Cha","Jonghwan Mun","Byungseok Roh"],"abstract":"We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive advances by employing contrastive learning (CL) to learn diverse visual concepts and transferring the learned image-level understanding to the segmentation task. However, these CL-based methods suffer from a train-test discrepancy, since it only considers image-text alignment during training, whereas segmentation requires region-text alignment during testing. In this paper, we proposed a novel Text-grounded Contrastive Learning (TCL) framework that enables a model to directly learn region-text alignment. Our method generates a segmentation mask for a given text, extracts text-grounded image embedding from the masked region, and aligns it with text embedding via TCL. By learning region-text alignment directly, our framework encourages a model to directly improve the quality of generated segmentation masks. In addition, for a rigorous and fair comparison, we present a unified evaluation protocol with widely used 8 semantic segmentation datasets. TCL achieves state-of-the-art zero-shot segmentation performances with large margins in all datasets. Code is available at https://github.com/kakaobrain/tcl.","url_abs":"https://arxiv.org/abs/2212.00785v2","url_pdf":"https://arxiv.org/pdf/2212.00785v2.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":"learning-to-generate-text-grounded-mask-for","repo_url":"https://github.com/kakaobrain/tcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-semantic-segmentation-with","task_name":"Unsupervised Semantic Segmentation with Language-image Pre-training"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-1","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-59","model":"TCL","rank_in_archive_order":22,"of":24,"metrics":{"mIoU":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-5","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20","model":"TCL","rank_in_archive_order":16,"of":20,"metrics":{"mIoU":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cc3m-tagmask","task":"Semantic Segmentation","dataset":"CC3M-TagMask","model":"TCL","rank_in_archive_order":2,"of":4,"metrics":{"mIoU":"60.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-4","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"ADE20K","model":"TCL","rank_in_archive_order":7,"of":13,"metrics":{"Mean IoU (val)":"17.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-10","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"COCO-Object","model":"TCL","rank_in_archive_order":7,"of":12,"metrics":{"mIoU":"31.6"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-9","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"COCO-Stuff-171","model":"TCL","rank_in_archive_order":8,"of":12,"metrics":{"mIoU":"22.4"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-3","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"Cityscapes val","model":"TCL","rank_in_archive_order":9,"of":12,"metrics":{"mIoU":"24.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-8","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PASCAL Context-59","model":"TCL","rank_in_archive_order":7,"of":12,"metrics":{"mIoU":"33.9"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-11","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PASCAL VOC","model":"TCL","rank_in_archive_order":7,"of":10,"metrics":{"mIoU":"55.0"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-semantic-segmentation-with-7","task":"Unsupervised Semantic Segmentation with Language-image Pre-training","dataset":"PascalVOC-20","model":"TCL","rank_in_archive_order":6,"of":10,"metrics":{"mIoU":"83.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.00785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00785"}},"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/kakaobrain/tcl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"790a4be48cafa62e","entry":"dispatcher","repo":"kakaobrain/tcl","repo_kind":"official","path":"models/tcl/modules.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/models/tcl/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"790a4be48cafa62e"}},{"code_sha256_prefix":"b5e9f34a53a178b5","entry":"activ_dispatch","repo":"kakaobrain/tcl","repo_kind":"official","path":"models/tcl/modules.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/models/tcl/modules.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":"b5e9f34a53a178b5"}},{"code_sha256_prefix":"97e9728dd347e1c0","entry":"build_model","repo":"kakaobrain/tcl","repo_kind":"official","path":"sclip/model.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/sclip/model.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":"97e9728dd347e1c0"}},{"code_sha256_prefix":"8b47bc6bde752577","entry":"get_norm_fn","repo":"kakaobrain/tcl","repo_kind":"official","path":"models/tcl/modules.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/models/tcl/modules.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":"8b47bc6bde752577"}},{"code_sha256_prefix":"9b85141da9c13ff7","entry":"gumbel_sigmoid","repo":"kakaobrain/tcl","repo_kind":"official","path":"models/tcl/gumbel.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/models/tcl/gumbel.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":"9b85141da9c13ff7"}},{"code_sha256_prefix":"eebb2dd2a89fe95e","entry":"interpolate_pos_emb","repo":"kakaobrain/tcl","repo_kind":"official","path":"sclip/model.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/sclip/model.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":"eebb2dd2a89fe95e"}},{"code_sha256_prefix":"84793d627e521db5","entry":"make_diag","repo":"kakaobrain/tcl","repo_kind":"official","path":"sclip/model.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/sclip/model.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":"84793d627e521db5"}},{"code_sha256_prefix":"33a6ac4097ed0ed5","entry":"tv_loss","repo":"kakaobrain/tcl","repo_kind":"official","path":"models/tcl/tcl.py","file_url":"https://github.com/kakaobrain/tcl/blob/HEAD/models/tcl/tcl.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":"33a6ac4097ed0ed5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}