{"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/nllb-clip-train-performant-multilingual-image","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","arxiv_id":"2309.01859","date":"2023-09-04","proceeding":null,"authors":["Alexander Visheratin"],"abstract":"Today, the exponential rise of large models developed by academic and industrial institutions with the help of massive computing resources raises the question of whether someone without access to such resources can make a valuable scientific contribution. To explore this, we tried to solve the challenging task of multilingual image retrieval having a limited budget of $1,000. As a result, we present NLLB-CLIP - CLIP model with a text encoder from the NLLB model. To train the model, we used an automatically created dataset of 106,246 good-quality images with captions in 201 languages derived from the LAION COCO dataset. We trained multiple models using image and text encoders of various sizes and kept different parts of the model frozen during the training. We thoroughly analyzed the trained models using existing evaluation datasets and newly created XTD200 and Flickr30k-200 datasets. We show that NLLB-CLIP is comparable in quality to state-of-the-art models and significantly outperforms them on low-resource languages.","url_abs":"https://arxiv.org/abs/2309.01859v3","url_pdf":"https://arxiv.org/pdf/2309.01859v3.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":"nllb-clip-train-performant-multilingual-image","repo_url":"https://github.com/eify/clip_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"nllb-clip-train-performant-multilingual-image","repo_url":"https://github.com/laion-ai/clip_benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"nllb-clip-train-performant-multilingual-image","repo_url":"https://github.com/pwc-1/Paper-5/tree/main/nllb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"nllb-clip-train-performant-multilingual-image","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/2/nllb","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.01859","atlas_url":"https://app.syntology.ai/?focus=2309.01859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.01859"}},"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/laion-ai/clip_benchmark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/2/nllb","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eify/clip_benchmark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-5/tree/main/nllb","reach":null}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"listed":{"samples":8,"ran":1,"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":"dbc602d6bfc435f3","entry":"get_dataset_default_task","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/datasets/builder.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/datasets/builder.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":true,"mcp_get_code":{"code_sha256":"dbc602d6bfc435f3"}},{"code_sha256_prefix":"27180e9964b8cac8","entry":"PIL_to_bytes","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/webdataset_builder.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/webdataset_builder.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":true,"mcp_get_code":{"code_sha256":"27180e9964b8cac8"}},{"code_sha256_prefix":"63b80a251f3277e4","entry":"build_dataset","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/datasets/builder.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/datasets/builder.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":true,"mcp_get_code":{"code_sha256":"63b80a251f3277e4"}},{"code_sha256_prefix":"f4eee6ad42516616","entry":"get_metadata","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/datasets/objectnet.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/datasets/objectnet.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":true,"mcp_get_code":{"code_sha256":"f4eee6ad42516616"}},{"code_sha256_prefix":"e02503f545c31203","entry":"get_model_collection_from_file","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/model_collection.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/model_collection.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":true,"mcp_get_code":{"code_sha256":"e02503f545c31203"}},{"code_sha256_prefix":"f5190e9b44c5f641","entry":"load_japanese_clip","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/models/japanese_clip.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/models/japanese_clip.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":true,"mcp_get_code":{"code_sha256":"f5190e9b44c5f641"}},{"code_sha256_prefix":"eb9c4da61c3f9683","entry":"path_to_bytes","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/webdataset_builder.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/webdataset_builder.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":true,"mcp_get_code":{"code_sha256":"eb9c4da61c3f9683"}},{"code_sha256_prefix":"9e8b17a3977b594e","entry":"value_from_first_key_found","repo":"eify/clip_benchmark","repo_kind":"listed","path":"clip_benchmark/datasets/builder.py","file_url":"https://github.com/eify/clip_benchmark/blob/HEAD/clip_benchmark/datasets/builder.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":true,"mcp_get_code":{"code_sha256":"9e8b17a3977b594e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}