{"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/transfer-learning-from-language-models-to","title":"Transfer learning from language models to image caption generators: Better models may not transfer better","arxiv_id":"1901.01216","date":"2019-01-01","proceeding":null,"authors":["Marc Tanti","Albert Gatt","Kenneth P. Camilleri"],"abstract":"When designing a neural caption generator, a convolutional neural network can\nbe used to extract image features. Is it possible to also use a neural language\nmodel to extract sentence prefix features? We answer this question by trying\ndifferent ways to transfer the recurrent neural network and embedding layer\nfrom a neural language model to an image caption generator. We find that image\ncaption generators with transferred parameters perform better than those\ntrained from scratch, even when simply pre-training them on the text of the\nsame captions dataset it will later be trained on. We also find that the best\nlanguage models (in terms of perplexity) do not result in the best caption\ngenerators after transfer learning.","url_abs":"http://arxiv.org/abs/1901.01216v1","url_pdf":"http://arxiv.org/pdf/1901.01216v1.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":"transfer-learning-from-language-models-to","repo_url":"https://github.com/mtanti/mtanti-phd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.01216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01216"}},"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/mtanti/mtanti-phd","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"596bef484c52bbc6","entry":"jsd","repo":"mtanti/mtanti-phd","repo_kind":"official","path":"experiments/thesis/imageimportance_experiment.py","file_url":"https://github.com/mtanti/mtanti-phd/blob/HEAD/experiments/thesis/imageimportance_experiment.py","link_basis":"first_harvest_node","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":"596bef484c52bbc6"}},{"code_sha256_prefix":"2981554ec0436183","entry":"preprocess_sent","repo":"mtanti/mtanti-phd","repo_kind":"official","path":"experiments/thesis/dataset_maker.py","file_url":"https://github.com/mtanti/mtanti-phd/blob/HEAD/experiments/thesis/dataset_maker.py","link_basis":"first_harvest_node","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":"2981554ec0436183"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}