{"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/hyperbolic-image-text-representations","title":"Hyperbolic Image-Text Representations","arxiv_id":"2304.09172","date":"2023-04-18","proceeding":null,"authors":["Karan Desai","Maximilian Nickel","Tanmay Rajpurohit","Justin Johnson","Ramakrishna Vedantam"],"abstract":"Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept \"dog\" entails all images that contain dogs. Despite being intuitive, current large-scale vision and language models such as CLIP do not explicitly capture such hierarchy. We propose MERU, a contrastive model that yields hyperbolic representations of images and text. Hyperbolic spaces have suitable geometric properties to embed tree-like data, so MERU can better capture the underlying hierarchy in image-text datasets. Our results show that MERU learns a highly interpretable and structured representation space while being competitive with CLIP's performance on standard multi-modal tasks like image classification and image-text retrieval. Our code and models are available at https://www.github.com/facebookresearch/meru","url_abs":"https://arxiv.org/abs/2304.09172v3","url_pdf":"https://arxiv.org/pdf/2304.09172v3.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":"hyperbolic-image-text-representations","repo_url":"https://github.com/facebookresearch/meru","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"hyperbolic-image-text-representations","repo_url":"https://github.com/naver-ai/hype","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-text-retrieval","task_name":"Image-text Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.09172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.09172"}},"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":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/slip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/naver-ai/hype","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/meru","reach":null}],"summary":{"ran_fixture":3,"ran_draft_wrong":2,"ran":1,"unverified":9},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1},"listed":{"samples":1,"ran":1,"repositories":1},"found_in_text":{"samples":12,"ran":5,"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":14,"samples":[{"code_sha256_prefix":"131a82fd65128218","entry":"accuracy","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"main_linear.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/main_linear.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"2e59707d16d21473","entry":"accuracy","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"eval_zeroshot.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/eval_zeroshot.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"2e59707d16d21473"}},{"code_sha256_prefix":"baf67fde22e8bbee","entry":"expm","repo":"naver-ai/hype","repo_kind":"listed","path":"hyperbolic.py","file_url":"https://github.com/naver-ai/hype/blob/HEAD/hyperbolic.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"baf67fde22e8bbee"}},{"code_sha256_prefix":"345ec4da9f331b85","entry":"get_metric_names","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/models.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"345ec4da9f331b85"}},{"code_sha256_prefix":"a3448702d6025ce6","entry":"get_num_layer_for_vit","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"beit_finetuning/optim_factory.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/beit_finetuning/optim_factory.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a3448702d6025ce6"}},{"code_sha256_prefix":"f0eb8193f86d363b","entry":"mean_per_class","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"eval_zeroshot.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/eval_zeroshot.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f0eb8193f86d363b"}},{"code_sha256_prefix":"834ebe823c8808e3","entry":"CLIPBaseline","repo":"facebookresearch/meru","repo_kind":"official","path":"meru/models.py","file_url":"https://github.com/facebookresearch/meru/blob/HEAD/meru/models.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":"834ebe823c8808e3"}},{"code_sha256_prefix":"37a4a089ca65adf3","entry":"MERU","repo":"facebookresearch/meru","repo_kind":"official","path":"meru/models.py","file_url":"https://github.com/facebookresearch/meru/blob/HEAD/meru/models.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":"37a4a089ca65adf3"}},{"code_sha256_prefix":"b700fb0a3496b255","entry":"cosine_scheduler","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"beit_finetuning/utils.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/beit_finetuning/utils.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":false,"mcp_get_code":{"code_sha256":"b700fb0a3496b255"}},{"code_sha256_prefix":"f4d9f26124e665f4","entry":"get_downstream_dataset","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"datasets.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/datasets.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":false,"mcp_get_code":{"code_sha256":"f4d9f26124e665f4"}},{"code_sha256_prefix":"0ef0019514eaaa09","entry":"get_parameter_groups","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"beit_finetuning/optim_factory.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/beit_finetuning/optim_factory.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":false,"mcp_get_code":{"code_sha256":"0ef0019514eaaa09"}},{"code_sha256_prefix":"41dbe0d4c6e1d565","entry":"pil_loader","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"datasets.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/datasets.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":false,"mcp_get_code":{"code_sha256":"41dbe0d4c6e1d565"}},{"code_sha256_prefix":"9c147228c1764edd","entry":"train","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"main_linear.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/main_linear.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":false,"mcp_get_code":{"code_sha256":"9c147228c1764edd"}},{"code_sha256_prefix":"3e77a098344bd525","entry":"validate","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"main_linear.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/main_linear.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":false,"mcp_get_code":{"code_sha256":"3e77a098344bd525"}},{"code_sha256_prefix":"3c4992378ca3d4d0","entry":"yfcc_loader","repo":"facebookresearch/slip","repo_kind":"found_in_text","path":"datasets.py","file_url":"https://github.com/facebookresearch/slip/blob/HEAD/datasets.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":false,"mcp_get_code":{"code_sha256":"3c4992378ca3d4d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}