{"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/iglue-a-benchmark-for-transfer-learning","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","arxiv_id":"2201.11732","date":"2022-01-27","proceeding":null,"authors":["Emanuele Bugliarello","Fangyu Liu","Jonas Pfeiffer","Siva Reddy","Desmond Elliott","Edoardo Maria Ponti","Ivan Vulić"],"abstract":"Reliable evaluation benchmarks designed for replicability and comprehensiveness have driven progress in machine learning. Due to the lack of a multilingual benchmark, however, vision-and-language research has mostly focused on English language tasks. To fill this gap, we introduce the Image-Grounded Language Understanding Evaluation benchmark. IGLUE brings together - by both aggregating pre-existing datasets and creating new ones - visual question answering, cross-modal retrieval, grounded reasoning, and grounded entailment tasks across 20 diverse languages. Our benchmark enables the evaluation of multilingual multimodal models for transfer learning, not only in a zero-shot setting, but also in newly defined few-shot learning setups. Based on the evaluation of the available state-of-the-art models, we find that translate-test transfer is superior to zero-shot transfer and that few-shot learning is hard to harness for many tasks. Moreover, downstream performance is partially explained by the amount of available unlabelled textual data for pretraining, and only weakly by the typological distance of target-source languages. We hope to encourage future research efforts in this area by releasing the benchmark to the community.","url_abs":"https://arxiv.org/abs/2201.11732v2","url_pdf":"https://arxiv.org/pdf/2201.11732v2.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":"iglue-a-benchmark-for-transfer-learning","repo_url":"https://github.com/e-bug/iglue","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"iglue-a-benchmark-for-transfer-learning","repo_url":"https://github.com/e-bug/volta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"iglue-a-benchmark-for-transfer-learning","repo_url":"https://github.com/shin-ee-chen/bla","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[{"slug":"iglue","name":"IGLUE","full_name":"Image-Grounded Language Understanding Evaluation"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.11732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.11732"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shin-ee-chen/bla","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/e-bug/volta","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/e-bug/iglue","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_fixture":1,"ran_honours":2,"unverified":13},"by_repo_kind":{"official":{"samples":21,"ran":8,"repositories":2}},"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":"0f786c407fb1ee4c","entry":"swish","repo":"e-bug/volta","repo_kind":"official","path":"volta/encoders.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/encoders.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"a3e27bd1e8b628ed","entry":"Embedding","repo":"e-bug/volta","repo_kind":"official","path":"volta/m3p_transformer.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/m3p_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a3e27bd1e8b628ed"}},{"code_sha256_prefix":"b5254f10aa821ab8","entry":"Linear","repo":"e-bug/volta","repo_kind":"official","path":"volta/m3p_transformer.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/m3p_transformer.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5254f10aa821ab8"}},{"code_sha256_prefix":"d4903874fdec3763","entry":"create_position_ids_from_input_ids","repo":"e-bug/volta","repo_kind":"official","path":"volta/embeddings.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/embeddings.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4903874fdec3763"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"e-bug/volta","repo_kind":"official","path":"volta/encoders.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/encoders.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"66c21a3911091d29","entry":"gelu","repo":"e-bug/volta","repo_kind":"official","path":"volta/m3p_transformer.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/m3p_transformer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66c21a3911091d29"}},{"code_sha256_prefix":"64fe66e56c74b1f6","entry":"resume","repo":"e-bug/volta","repo_kind":"official","path":"volta/train_utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/train_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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"64fe66e56c74b1f6"}},{"code_sha256_prefix":"5eff22fa0a651276","entry":"url_to_filename","repo":"e-bug/volta","repo_kind":"official","path":"volta/utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/utils.py","link_basis":"harvester_set","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":"5eff22fa0a651276"}},{"code_sha256_prefix":"07cb4167108cab0b","entry":"ForwardModelsVal","repo":"e-bug/volta","repo_kind":"official","path":"volta/task_utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/task_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":true,"mcp_get_code":{"code_sha256":"07cb4167108cab0b"}},{"code_sha256_prefix":"085e162f35b24d79","entry":"LoadLoss","repo":"e-bug/volta","repo_kind":"official","path":"volta/task_utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/task_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":true,"mcp_get_code":{"code_sha256":"085e162f35b24d79"}},{"code_sha256_prefix":"1873b62b661f9fda","entry":"cached_path","repo":"e-bug/volta","repo_kind":"official","path":"volta/utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/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":true,"mcp_get_code":{"code_sha256":"1873b62b661f9fda"}},{"code_sha256_prefix":"4c2f89511d326a22","entry":"collate_fn","repo":"e-bug/iglue","repo_kind":"official","path":"features_extraction/detectron2_proposal_maxnms.py","file_url":"https://github.com/e-bug/iglue/blob/HEAD/features_extraction/detectron2_proposal_maxnms.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":"4c2f89511d326a22"}},{"code_sha256_prefix":"58c8b6cbad44801a","entry":"coordinate_embeddings","repo":"e-bug/volta","repo_kind":"official","path":"volta/embeddings.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/embeddings.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":"58c8b6cbad44801a"}},{"code_sha256_prefix":"82874b46e206faf3","entry":"filename_to_url","repo":"e-bug/volta","repo_kind":"official","path":"volta/utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/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":true,"mcp_get_code":{"code_sha256":"82874b46e206faf3"}},{"code_sha256_prefix":"9499ed1255d97132","entry":"iou","repo":"e-bug/volta","repo_kind":"official","path":"volta/datasets/concept_cap_dataset.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/datasets/concept_cap_dataset.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":"9499ed1255d97132"}},{"code_sha256_prefix":"a2faafba33358747","entry":"kl_1601","repo":"e-bug/volta","repo_kind":"official","path":"volta/losses.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/losses.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":"a2faafba33358747"}},{"code_sha256_prefix":"fd48f6a6c3aa0b29","entry":"load_obj_tsv","repo":"e-bug/iglue","repo_kind":"official","path":"features_extraction/tsv_to_h5.py","file_url":"https://github.com/e-bug/iglue/blob/HEAD/features_extraction/tsv_to_h5.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":"fd48f6a6c3aa0b29"}},{"code_sha256_prefix":"baa5766f4566aafc","entry":"load_tf_weights_in_bert","repo":"e-bug/volta","repo_kind":"official","path":"volta/encoders.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/encoders.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":"baa5766f4566aafc"}},{"code_sha256_prefix":"1adf127958517c64","entry":"mse_2048","repo":"e-bug/volta","repo_kind":"official","path":"volta/losses.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/losses.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":"1adf127958517c64"}},{"code_sha256_prefix":"60cab169db54e986","entry":"nce_2048","repo":"e-bug/volta","repo_kind":"official","path":"volta/losses.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/losses.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":"60cab169db54e986"}},{"code_sha256_prefix":"b8c86cabecffbff9","entry":"triplet_loss","repo":"e-bug/volta","repo_kind":"official","path":"volta/task_utils.py","file_url":"https://github.com/e-bug/volta/blob/HEAD/volta/task_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":true,"mcp_get_code":{"code_sha256":"b8c86cabecffbff9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}