{"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/head2toe-utilizing-intermediate-1","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","arxiv_id":"2201.03529","date":"2022-01-10","proceeding":null,"authors":["Utku Evci","Vincent Dumoulin","Hugo Larochelle","Michael C. Mozer"],"abstract":"Transfer-learning methods aim to improve performance in a data-scarce target domain using a model pretrained on a data-rich source domain. A cost-efficient strategy, linear probing, involves freezing the source model and training a new classification head for the target domain. This strategy is outperformed by a more costly but state-of-the-art method -- fine-tuning all parameters of the source model to the target domain -- possibly because fine-tuning allows the model to leverage useful information from intermediate layers which is otherwise discarded by the later pretrained layers. We explore the hypothesis that these intermediate layers might be directly exploited. We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain. In evaluations on the VTAB-1k, Head2Toe matches performance obtained with fine-tuning on average while reducing training and storage cost hundred folds or more, but critically, for out-of-distribution transfer, Head2Toe outperforms fine-tuning.","url_abs":"https://arxiv.org/abs/2201.03529v2","url_pdf":"https://arxiv.org/pdf/2201.03529v2.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":"head2toe-utilizing-intermediate-1","repo_url":"https://github.com/google-research/head2toe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"head2toe-utilizing-intermediate-1","repo_url":"https://github.com/arkel23/clca","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2201.03529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.03529"}},"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/arkel23/clca","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/head2toe","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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":"c6a17020a0c3527e","entry":"flatten_and_concat","repo":"google-research/head2toe","repo_kind":"official","path":"head2toe/models/finetune.py","file_url":"https://github.com/google-research/head2toe/blob/HEAD/head2toe/models/finetune.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6a17020a0c3527e"}},{"code_sha256_prefix":"8e7fb3ab0f36d631","entry":"zero_aware_normalize","repo":"google-research/head2toe","repo_kind":"official","path":"head2toe/models/finetune.py","file_url":"https://github.com/google-research/head2toe/blob/HEAD/head2toe/models/finetune.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e7fb3ab0f36d631"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}