{"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/semivl-semi-supervised-semantic-segmentation","title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","arxiv_id":"2311.16241","date":"2023-11-27","proceeding":null,"authors":["Lukas Hoyer","David Joseph Tan","Muhammad Ferjad Naeem","Luc van Gool","Federico Tombari"],"abstract":"In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good segmentation boundaries, they are prone to confuse classes with similar visual appearance due to the limited supervision. On the other hand, vision-language models (VLMs) are able to learn diverse semantic knowledge from image-caption datasets but produce noisy segmentation due to the image-level training. In SemiVL, we propose to integrate rich priors from VLM pre-training into semi-supervised semantic segmentation to learn better semantic decision boundaries. To adapt the VLM from global to local reasoning, we introduce a spatial fine-tuning strategy for label-efficient learning. Further, we design a language-guided decoder to jointly reason over vision and language. Finally, we propose to handle inherent ambiguities in class labels by providing the model with language guidance in the form of class definitions. We evaluate SemiVL on 4 semantic segmentation datasets, where it significantly outperforms previous semi-supervised methods. For instance, SemiVL improves the state-of-the-art by +13.5 mIoU on COCO with 232 annotated images and by +6.1 mIoU on Pascal VOC with 92 labels. Project page: https://github.com/google-research/semivl","url_abs":"https://arxiv.org/abs/2311.16241v1","url_pdf":"https://arxiv.org/pdf/2311.16241v1.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":"semivl-semi-supervised-semantic-segmentation","repo_url":"https://github.com/google-research/semivl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"semi-supervised-semantic-segmentation","task_name":"Semi-Supervised Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-42","task":"Semi-Supervised Semantic Segmentation","dataset":"ADE20K 1/16 labeled","model":"SemiVL","rank_in_archive_order":2,"of":5,"metrics":{"Validation mIoU":"37.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-41","task":"Semi-Supervised Semantic Segmentation","dataset":"ADE20K 1/32 labeled","model":"SemiVL","rank_in_archive_order":2,"of":5,"metrics":{"Validation mIoU":"35.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-2","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/128 labeled","model":"SemiVL","rank_in_archive_order":2,"of":9,"metrics":{"Validation mIoU":"53.6"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-1","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/256 labeled","model":"SemiVL","rank_in_archive_order":2,"of":9,"metrics":{"Validation mIoU":"52.8"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-4","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/32 labeled","model":"SemiVL","rank_in_archive_order":2,"of":7,"metrics":{"Validation mIoU":"56.5"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/512 labeled","model":"SemiVL","rank_in_archive_order":1,"of":8,"metrics":{"Validation mIoU":"50.1"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-coco-3","task":"Semi-Supervised Semantic Segmentation","dataset":"COCO 1/64 labeled","model":"SemiVL","rank_in_archive_order":2,"of":9,"metrics":{"Validation mIoU":"55.4"},"uses_additional_data":true},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-3","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 100 samples labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":1,"of":13,"metrics":{"Validation mIoU":"76.2"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-2","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 12.5% labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":2,"of":33,"metrics":{"Validation mIoU":"79.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-1","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 25% labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":2,"of":30,"metrics":{"Validation mIoU":"80.3%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-8","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 50% labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":3,"of":23,"metrics":{"Validation mIoU":"80.6%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-22","task":"Semi-Supervised Semantic Segmentation","dataset":"Cityscapes 6.25% labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":2,"of":18,"metrics":{"Validation mIoU":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-10","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 1464 labels","model":"SemiVL (ViT-B/16","rank_in_archive_order":3,"of":17,"metrics":{"Validation mIoU":"87.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-10","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 1464 labels","model":"UniMatch (ViT-B/16)","rank_in_archive_order":4,"of":17,"metrics":{"Validation mIoU":"84.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-28","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 183 labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":3,"of":16,"metrics":{"Validation mIoU":"85.6"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-28","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 183 labeled","model":"UniMatch (ViT-B/16)","rank_in_archive_order":5,"of":16,"metrics":{"Validation mIoU":"80.1"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-29","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 366 labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":3,"of":15,"metrics":{"Validation mIoU":"86.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-29","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 366 labeled","model":"UniMatch (ViT-B/16)","rank_in_archive_order":4,"of":15,"metrics":{"Validation mIoU":"82.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-30","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 732 labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":3,"of":16,"metrics":{"Validation mIoU":"86.7"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-30","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 732 labeled","model":"UniMatch (ViT-B/16)","rank_in_archive_order":4,"of":16,"metrics":{"Validation mIoU":"83.3"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-27","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 92 labeled","model":"SemiVL (ViT-B/16)","rank_in_archive_order":3,"of":17,"metrics":{"Validation mIoU":"84.0"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-semantic-segmentation-on-27","task":"Semi-Supervised Semantic Segmentation","dataset":"PASCAL VOC 2012 92 labeled","model":"UniMatch (ViT-B/16)","rank_in_archive_order":6,"of":17,"metrics":{"Validation mIoU":"77.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.16241","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}