{"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/asif-coupled-data-turns-unimodal-models-to-1","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","arxiv_id":"2210.01738","date":"2022-10-04","proceeding":"NeurIPS 2023 11","authors":["Antonio Norelli","Marco Fumero","Valentino Maiorca","Luca Moschella","Emanuele Rodolà","Francesco Locatello"],"abstract":"CLIP proved that aligning visual and language spaces is key to solving many vision tasks without explicit training, but required to train image and text encoders from scratch on a huge dataset. LiT improved this by only training the text encoder and using a pre-trained vision network. In this paper, we show that a common space can be created without any training at all, using single-domain encoders (trained with or without supervision) and a much smaller amount of image-text pairs. Furthermore, our model has unique properties. Most notably, deploying a new version with updated training samples can be done in a matter of seconds. Additionally, the representations in the common space are easily interpretable as every dimension corresponds to the similarity of the input to a unique image-text pair in the multimodal dataset. Experiments on standard zero-shot visual benchmarks demonstrate the typical transfer ability of image-text models. Overall, our method represents a simple yet surprisingly strong baseline for foundation multimodal models, raising important questions on their data efficiency and on the role of retrieval in machine learning.","url_abs":"https://arxiv.org/abs/2210.01738v3","url_pdf":"https://arxiv.org/pdf/2210.01738v3.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":"asif-coupled-data-turns-unimodal-models-to-1","repo_url":"https://github.com/noranta4/asif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.01738","atlas_url":"https://app.syntology.ai/?focus=2210.01738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01738"}},"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/noranta4/asif","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6},"by_repo_kind":{"listed":{"samples":6,"ran":6,"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":"7c632bc5e17a2972","entry":"embeddings_from_dl","repo":"noranta4/asif","repo_kind":"listed","path":"relrepsutils.py","file_url":"https://github.com/noranta4/asif/blob/HEAD/relrepsutils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7c632bc5e17a2972"}},{"code_sha256_prefix":"4b3349d96f56b8d4","entry":"load_images_in_dl","repo":"noranta4/asif","repo_kind":"listed","path":"relrepsutils.py","file_url":"https://github.com/noranta4/asif/blob/HEAD/relrepsutils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b3349d96f56b8d4"}},{"code_sha256_prefix":"0b5d2712751476be","entry":"normalize_sparse","repo":"noranta4/asif","repo_kind":"listed","path":"relreps.py","file_url":"https://github.com/noranta4/asif/blob/HEAD/relreps.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b5d2712751476be"}},{"code_sha256_prefix":"aed4e5490fc088dc","entry":"relative_represent","repo":"noranta4/asif","repo_kind":"listed","path":"relreps.py","file_url":"https://github.com/noranta4/asif/blob/HEAD/relreps.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aed4e5490fc088dc"}},{"code_sha256_prefix":"b2e3d82412c09f49","entry":"sparsify","repo":"noranta4/asif","repo_kind":"listed","path":"relreps.py","file_url":"https://github.com/noranta4/asif/blob/HEAD/relreps.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2e3d82412c09f49"}},{"code_sha256_prefix":"9dc15dd5fec40d34","entry":"transform_image","repo":"noranta4/asif","repo_kind":"listed","path":"relrepsutils.py","file_url":"https://github.com/noranta4/asif/blob/HEAD/relrepsutils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9dc15dd5fec40d34"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}