{"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/logme-practical-assessment-of-pre-trained","title":"LogME: Practical Assessment of Pre-trained Models for Transfer Learning","arxiv_id":"2102.11005","date":"2021-02-22","proceeding":null,"authors":["Kaichao You","Yong liu","Jianmin Wang","Mingsheng Long"],"abstract":"This paper studies task adaptive pre-trained model selection, an underexplored problem of assessing pre-trained models for the target task and select best ones from the model zoo \\emph{without fine-tuning}. A few pilot works addressed the problem in transferring supervised pre-trained models to classification tasks, but they cannot handle emerging unsupervised pre-trained models or regression tasks. In pursuit of a practical assessment method, we propose to estimate the maximum value of label evidence given features extracted by pre-trained models. Unlike the maximum likelihood, the maximum evidence is \\emph{immune to over-fitting}, while its expensive computation can be dramatically reduced by our carefully designed algorithm. The Logarithm of Maximum Evidence (LogME) can be used to assess pre-trained models for transfer learning: a pre-trained model with a high LogME value is likely to have good transfer performance. LogME is \\emph{fast, accurate, and general}, characterizing itself as the first practical method for assessing pre-trained models. Compared with brute-force fine-tuning, LogME brings at most $3000\\times$ speedup in wall-clock time and requires only $1\\%$ memory footprint. It outperforms prior methods by a large margin in their setting and is applicable to new settings. It is general enough for diverse pre-trained models (supervised pre-trained and unsupervised pre-trained), downstream tasks (classification and regression), and modalities (vision and language). Code is available at this repository: \\href{https://github.com/thuml/LogME}{https://github.com/thuml/LogME}.","url_abs":"https://arxiv.org/abs/2102.11005v3","url_pdf":"https://arxiv.org/pdf/2102.11005v3.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":"logme-practical-assessment-of-pre-trained","repo_url":"https://github.com/thuml/LogME","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"model-selection","task_name":"Model Selection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"transferability","task_name":"Transferability"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/transferability-on-classification-benchmark","task":"Transferability","dataset":"classification benchmark","model":"logme","rank_in_archive_order":3,"of":6,"metrics":{"Kendall's Tau":"0.482"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.11005","atlas_url":"https://app.syntology.ai/?focus=2102.11005","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11005"}},"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":"deterministic:regex_extraction","url":"https://github.com/thuml/LogME","reach":null}],"summary":{"ran_draft_wrong":2,"ran":1,"ran_fixture":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"9ff1588d86660d6d","entry":"str2list","repo":"thuml/LogME","repo_kind":"official","path":"b_tuning.py","file_url":"https://github.com/thuml/LogME/blob/HEAD/b_tuning.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ff1588d86660d6d"}},{"code_sha256_prefix":"fce5c449bff0ff4b","entry":"LogME","repo":"thuml/LogME","repo_kind":"official","path":"LogME.py","file_url":"https://github.com/thuml/LogME/blob/HEAD/LogME.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fce5c449bff0ff4b"}},{"code_sha256_prefix":"cd55b5db902308f3","entry":"each_evidence","repo":"thuml/LogME","repo_kind":"official","path":"LogME.py","file_url":"https://github.com/thuml/LogME/blob/HEAD/LogME.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd55b5db902308f3"}},{"code_sha256_prefix":"a9c43aaa49888a3f","entry":"forward_pass","repo":"thuml/LogME","repo_kind":"official","path":"ranking.py","file_url":"https://github.com/thuml/LogME/blob/HEAD/ranking.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9c43aaa49888a3f"}},{"code_sha256_prefix":"25c7475539e39da4","entry":"str2bool","repo":"thuml/LogME","repo_kind":"official","path":"b_tuning.py","file_url":"https://github.com/thuml/LogME/blob/HEAD/b_tuning.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25c7475539e39da4"}},{"code_sha256_prefix":"711e681b397f724b","entry":"truncated_svd","repo":"thuml/LogME","repo_kind":"official","path":"LogME.py","file_url":"https://github.com/thuml/LogME/blob/HEAD/LogME.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"711e681b397f724b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}