{"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/prompt-based-multi-modal-image-segmentation","title":"Image Segmentation Using Text and Image Prompts","arxiv_id":"2112.10003","date":"2021-12-18","proceeding":"CVPR 2022 1","authors":["Timo Lüddecke","Alexander S. Ecker"],"abstract":"Image segmentation is usually addressed by training a model for a fixed set of object classes. Incorporating additional classes or more complex queries later is expensive as it requires re-training the model on a dataset that encompasses these expressions. Here we propose a system that can generate image segmentations based on arbitrary prompts at test time. A prompt can be either a text or an image. This approach enables us to create a unified model (trained once) for three common segmentation tasks, which come with distinct challenges: referring expression segmentation, zero-shot segmentation and one-shot segmentation. We build upon the CLIP model as a backbone which we extend with a transformer-based decoder that enables dense prediction. After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query. We analyze different variants of the latter image-based prompts in detail. This novel hybrid input allows for dynamic adaptation not only to the three segmentation tasks mentioned above, but to any binary segmentation task where a text or image query can be formulated. Finally, we find our system to adapt well to generalized queries involving affordances or properties. Code is available at https://eckerlab.org/code/clipseg.","url_abs":"https://arxiv.org/abs/2112.10003v2","url_pdf":"https://arxiv.org/pdf/2112.10003v2.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":"prompt-based-multi-modal-image-segmentation","repo_url":"https://github.com/timojl/clipseg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"prompt-based-multi-modal-image-segmentation","repo_url":"https://github.com/casia-iva-lab/fastsam","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"prompt-based-multi-modal-image-segmentation","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"prompt-based-multi-modal-image-segmentation","repo_url":"https://github.com/openrobotlab/ov_parts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"prompt-based-multi-modal-image-segmentation","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/clipseg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"prompt-based-multi-modal-image-segmentation","repo_url":"https://github.com/MindSpore-scientific/code-7/tree/main/ImageGPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"multi-modal-image-segmentation","task_name":"Multi-modal image segmentation"},{"task_slug":"one-shot-segmentation","task_name":"One-Shot Segmentation"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-image-matting-expression-based","task_name":"Referring Image Matting (Expression-based)"},{"task_slug":"referring-image-matting-keyword-based","task_name":"Referring Image Matting (Keyword-based)"},{"task_slug":"referring-image-matting-refmatte-rw100","task_name":"Referring Image Matting (RefMatte-RW100)"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-image-matting-expression-based-on","task":"Referring Image Matting (Expression-based)","dataset":"RefMatte","model":"CLIPSeg (ViT-B/16)","rank_in_archive_order":3,"of":4,"metrics":{"MAD":"0.0394","MAD(E)":"0.0419","MSE":"0.0358","MSE(E)":"0.0381","SAD":"69.13","SAD(E)":"73.53"},"uses_additional_data":false},{"leaderboard":"/sota/referring-image-matting-keyword-based-on","task":"Referring Image Matting (Keyword-based)","dataset":"RefMatte","model":"CLIPSeg (ViT-B/16)","rank_in_archive_order":3,"of":4,"metrics":{"MAD":"0.0101","MAD(E)":"0.0106","MSE":"0.0064","MSE(E)":"0.0067","SAD":"17.75","SAD(E)":"18.69"},"uses_additional_data":false},{"leaderboard":"/sota/referring-image-matting-refmatte-rw100-on","task":"Referring Image Matting (RefMatte-RW100)","dataset":"RefMatte","model":"CLIPSeg (ViT-B/16)","rank_in_archive_order":4,"of":4,"metrics":{"MAD":"0.1222","MAD(E)":"0.1282","MSE":"0.1178","MSE(E)":"0.1236","SAD":"211.86","SAD(E)":"222.37"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.10003","atlas_url":"https://app.syntology.ai/?focus=2112.10003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10003"}},"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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-7/tree/main/ImageGPT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openrobotlab/ov_parts","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/casia-iva-lab/fastsam","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/timojl/clipseg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/clipseg","reach":null}],"summary":{"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"057d183d358d1e9a","entry":"cosine_warmup_lr","repo":"timojl/clipseg","repo_kind":"official","path":"training.py","file_url":"https://github.com/timojl/clipseg/blob/HEAD/training.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"057d183d358d1e9a"}},{"code_sha256_prefix":"c78a6fe00b0a118f","entry":"get_cached_pascal_pfe","repo":"timojl/clipseg","repo_kind":"official","path":"score.py","file_url":"https://github.com/timojl/clipseg/blob/HEAD/score.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c78a6fe00b0a118f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}