{"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/explicit-inductive-bias-for-transfer-learning","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","arxiv_id":"1802.01483","date":"2018-02-05","proceeding":"ICML 2018 7","authors":["Xuhong Li","Yves GRANDVALET","Franck DAVOINE"],"abstract":"In inductive transfer learning, fine-tuning pre-trained convolutional\nnetworks substantially outperforms training from scratch. When using\nfine-tuning, the underlying assumption is that the pre-trained model extracts\ngeneric features, which are at least partially relevant for solving the target\ntask, but would be difficult to extract from the limited amount of data\navailable on the target task. However, besides the initialization with the\npre-trained model and the early stopping, there is no mechanism in fine-tuning\nfor retaining the features learned on the source task. In this paper, we\ninvestigate several regularization schemes that explicitly promote the\nsimilarity of the final solution with the initial model. We show the benefit of\nhaving an explicit inductive bias towards the initial model, and we eventually\nrecommend a simple $L^2$ penalty with the pre-trained model being a reference\nas the baseline of penalty for transfer learning tasks.","url_abs":"http://arxiv.org/abs/1802.01483v2","url_pdf":"http://arxiv.org/pdf/1802.01483v2.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":"explicit-inductive-bias-for-transfer-learning","repo_url":"https://github.com/holyseven/PSPNet-TF-Reproduce","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"explicit-inductive-bias-for-transfer-learning","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"explicit-inductive-bias-for-transfer-learning","repo_url":"https://github.com/timmywanttolearn/fintune","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.01483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.01483"}},"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/thuml/Transfer-Learning-Library","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/holyseven/PSPNet-TF-Reproduce","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/timmywanttolearn/fintune","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{},"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":2,"samples":[{"code_sha256_prefix":"977995a57dc87d8a","entry":"coloring_image_create","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"977995a57dc87d8a"}},{"code_sha256_prefix":"a1fe1d6979c55a18","entry":"prediction_image_create","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a1fe1d6979c55a18"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}