{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/2112-14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","arxiv_id":"2112.14757","date":"2021-12-29","proceeding":null,"authors":["Mengde Xu","Zheng Zhang","Fangyun Wei","Yutong Lin","Yue Cao","Han Hu","Xiang Bai"],"abstract":"Recently, open-vocabulary image classification by vision language pre-training has demonstrated incredible achievements, that the model can classify arbitrary categories without seeing additional annotated images of that category. However, it is still unclear how to make the open-vocabulary recognition work well on broader vision problems. This paper targets open-vocabulary semantic segmentation by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images. To remedy the discrepancy in processing granularity, we refuse the use of the prevalent one-stage FCN based framework, and advocate a two-stage semantic segmentation framework, with the first stage extracting generalizable mask proposals and the second stage leveraging an image based CLIP model to perform open-vocabulary classification on the masked image crops which are generated in the first stage. Our experimental results show that this two-stage framework can achieve superior performance than FCN when trained only on COCO Stuff dataset and evaluated on other datasets without fine-tuning. Moreover, this simple framework also surpasses previous state-of-the-arts of zero-shot semantic segmentation by a large margin: +29.5 hIoU on the Pascal VOC 2012 dataset, and +8.9 hIoU on the COCO Stuff dataset. With its simplicity and strong performance, we hope this framework to serve as a baseline to facilitate future research. The code are made publicly available at~\\url{https://github.com/MendelXu/zsseg.baseline}.","url_abs":"https://arxiv.org/abs/2112.14757v2","url_pdf":"https://arxiv.org/pdf/2112.14757v2.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":"2112-14757","repo_url":"https://github.com/mendelxu/zsseg.baseline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"2112-14757","repo_url":"https://github.com/openrobotlab/ov_parts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"open-vocabulary-image-classification","task_name":"Open Vocabulary Image Classification"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"open-vocabulary-semantic-segmentation-1","task_name":"Open-Vocabulary Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"zero-shot-image-classification","task_name":"Zero-Shot Image Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-semantic-segmentation","task_name":"Zero-Shot Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-2","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-150","model":"SimSeg","rank_in_archive_order":20,"of":23,"metrics":{"mIoU":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-3","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-847","model":"SimSeg","rank_in_archive_order":19,"of":19,"metrics":{"mIoU":"7"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-coco","task":"Open Vocabulary Semantic Segmentation","dataset":"COCO-Stuff-171","model":"ZSSeg","rank_in_archive_order":2,"of":7,"metrics":{"HIoU":"37.8"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on","task":"Open Vocabulary Semantic Segmentation","dataset":"Cityscapes","model":"SimSeg","rank_in_archive_order":2,"of":5,"metrics":{"mIoU":"34.5"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-1","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-59","model":"SimSeg","rank_in_archive_order":17,"of":24,"metrics":{"mIoU":"47.7"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-5","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20","model":"ZSSeg","rank_in_archive_order":19,"of":20,"metrics":{"hIoU":"77.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-coco-stuff","task":"Zero-Shot Semantic Segmentation","dataset":"COCO-Stuff","model":"zsseg","rank_in_archive_order":8,"of":15,"metrics":{"Inductive Setting hIoU":"36.3","Transductive Setting hIoU":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-pascal-voc","task":"Zero-Shot Semantic Segmentation","dataset":"PASCAL VOC","model":"zsseg","rank_in_archive_order":7,"of":13,"metrics":{"Inductive Setting hIoU":"77.5","Transductive Setting hIoU":"79.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.14757","atlas_url":"https://app.syntology.ai/?focus=2112.14757","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2112.14757"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.14757\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.14757"},"call":"get_concepts_for_paper(arxiv_id=\"2112.14757\")"}],"by_repo":[{"repo":"mendelxu/zsseg.baseline","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["136890725"],"harvested_for_calls":[]},{"repo":"openrobotlab/ov_parts","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.05107"],"harvested_for_calls":[{"arxiv_id":"2310.05107","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.05107"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.05107\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b20eec27c2e78d64040c266d7c03cb9998c46e70ec90c7f034d73efa946df5a2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}