{"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/distill-the-image-to-nowhere-inversion","title":"Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine Translation","arxiv_id":"2210.04468","date":"2022-10-10","proceeding":null,"authors":["Ru Peng","Yawen Zeng","Junbo Zhao"],"abstract":"Past works on multimodal machine translation (MMT) elevate bilingual setup by incorporating additional aligned vision information. However, an image-must requirement of the multimodal dataset largely hinders MMT's development -- namely that it demands an aligned form of [image, source text, target text]. This limitation is generally troublesome during the inference phase especially when the aligned image is not provided as in the normal NMT setup. Thus, in this work, we introduce IKD-MMT, a novel MMT framework to support the image-free inference phase via an inversion knowledge distillation scheme. In particular, a multimodal feature generator is executed with a knowledge distillation module, which directly generates the multimodal feature from (only) source texts as the input. While there have been a few prior works entertaining the possibility to support image-free inference for machine translation, their performances have yet to rival the image-must translation. In our experiments, we identify our method as the first image-free approach to comprehensively rival or even surpass (almost) all image-must frameworks, and achieved the state-of-the-art result on the often-used Multi30k benchmark. Our code and data are available at: https://github.com/pengr/IKD-mmt/tree/master..","url_abs":"https://arxiv.org/abs/2210.04468v2","url_pdf":"https://arxiv.org/pdf/2210.04468v2.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":"distill-the-image-to-nowhere-inversion","repo_url":"https://github.com/pengr/ikd-mmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multimodal-machine-translation","task_name":"Multimodal Machine Translation"},{"task_slug":"nmt","task_name":"NMT"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-machine-translation-on-multi30k","task":"Multimodal Machine Translation","dataset":"Multi30K","model":"IKD-MMT","rank_in_archive_order":2,"of":15,"metrics":{"BLEU (EN-DE)":"41.28","Meteor (EN-DE)":"58.93","Meteor (EN-FR)":"77.20"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.04468","atlas_url":"https://app.syntology.ai/?focus=2210.04468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.04468"}},"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/pengr/ikd-mmt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/multi30k/dataset","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"96cbb5e9ca5b6be0","entry":"Embedding","repo":"pengr/ikd-mmt","repo_kind":"official","path":"fairseq/models/transformer_mmt.py","file_url":"https://github.com/pengr/ikd-mmt/blob/HEAD/fairseq/models/transformer_mmt.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":false,"mcp_get_code":{"code_sha256":"96cbb5e9ca5b6be0"}},{"code_sha256_prefix":"8cd8cb0d1e9e63e4","entry":"Linear","repo":"pengr/ikd-mmt","repo_kind":"official","path":"fairseq/models/transformer_mmt.py","file_url":"https://github.com/pengr/ikd-mmt/blob/HEAD/fairseq/models/transformer_mmt.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":false,"mcp_get_code":{"code_sha256":"8cd8cb0d1e9e63e4"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"pengr/ikd-mmt","repo_kind":"official","path":"myresnet.py","file_url":"https://github.com/pengr/ikd-mmt/blob/HEAD/myresnet.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":false,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"pengr/ikd-mmt","repo_kind":"official","path":"myresnet.py","file_url":"https://github.com/pengr/ikd-mmt/blob/HEAD/myresnet.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":false,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"dec94511603455c6","entry":"deconv4x4","repo":"pengr/ikd-mmt","repo_kind":"official","path":"myresnet.py","file_url":"https://github.com/pengr/ikd-mmt/blob/HEAD/myresnet.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":"dec94511603455c6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}