{"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/inject-semantic-concepts-into-image-tagging","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","arxiv_id":"2310.15200","date":"2023-10-23","proceeding":null,"authors":["Xinyu Huang","Yi-Jie Huang","Youcai Zhang","Weiwei Tian","Rui Feng","Yuejie Zhang","Yanchun Xie","Yaqian Li","Lei Zhang"],"abstract":"In this paper, we introduce the Recognize Anything Plus Model (RAM++), an open-set image tagging model effectively leveraging multi-grained text supervision. Previous approaches (e.g., CLIP) primarily utilize global text supervision paired with images, leading to sub-optimal performance in recognizing multiple individual semantic tags. In contrast, RAM++ seamlessly integrates individual tag supervision with global text supervision, all within a unified alignment framework. This integration not only ensures efficient recognition of predefined tag categories, but also enhances generalization capabilities for diverse open-set categories. Furthermore, RAM++ employs large language models (LLMs) to convert semantically constrained tag supervision into more expansive tag description supervision, thereby enriching the scope of open-set visual description concepts. Comprehensive evaluations on various image recognition benchmarks demonstrate RAM++ exceeds existing state-of-the-art (SOTA) open-set image tagging models on most aspects. Specifically, for predefined commonly used tag categories, RAM++ showcases 10.2 mAP and 15.4 mAP enhancements over CLIP on OpenImages and ImageNet. For open-set categories beyond predefined, RAM++ records improvements of 5.0 mAP and 6.4 mAP over CLIP and RAM respectively on OpenImages. For diverse human-object interaction phrases, RAM++ achieves 7.8 mAP and 4.7 mAP improvements on the HICO benchmark. Code, datasets and pre-trained models are available at \\url{https://github.com/xinyu1205/recognize-anything}.","url_abs":"https://arxiv.org/abs/2310.15200v2","url_pdf":"https://arxiv.org/pdf/2310.15200v2.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":"inject-semantic-concepts-into-image-tagging","repo_url":"https://github.com/xinyu1205/recognize-anything","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"inject-semantic-concepts-into-image-tagging","repo_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"open-set-learning","task_name":"Open Set Learning"},{"task_slug":"tag","task_name":"TAG"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.15200","atlas_url":"https://app.syntology.ai/?focus=2310.15200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15200"}},"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/xinyu1205/recognize-anything","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_fixture":1,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":8,"ran":4,"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":"f353ed820c52e757","entry":"analyze_tags","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"generate_tag_des_llm.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/generate_tag_des_llm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f353ed820c52e757"}},{"code_sha256_prefix":"aa81d03f07735ab8","entry":"compute_acc","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa81d03f07735ab8"}},{"code_sha256_prefix":"ad12a494674d23fb","entry":"compute_n_params","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ad12a494674d23fb"}},{"code_sha256_prefix":"72ad4e7fb0db403a","entry":"load_thresholds","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"batch_inference.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/batch_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72ad4e7fb0db403a"}},{"code_sha256_prefix":"d177fece39702221","entry":"get_class_idxs","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"batch_inference.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/batch_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d177fece39702221"}},{"code_sha256_prefix":"a5e907771ca7b5d7","entry":"inference_ram","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"ram/inference.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/ram/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a5e907771ca7b5d7"}},{"code_sha256_prefix":"cc4cd40ee7f7cce8","entry":"inference_ram_openset","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"ram/inference.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/ram/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc4cd40ee7f7cce8"}},{"code_sha256_prefix":"3d89c9c107a089ad","entry":"inference_tag2text","repo":"xinyu1205/Recognize_Anything-Tag2Text","repo_kind":"listed","path":"ram/inference.py","file_url":"https://github.com/xinyu1205/Recognize_Anything-Tag2Text/blob/HEAD/ram/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3d89c9c107a089ad"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}