{"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/lipsum-ft-robust-fine-tuning-of-zero-shot","title":"Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance","arxiv_id":"2404.00860","date":"2024-04-01","proceeding":null,"authors":["Giung Nam","Byeongho Heo","Juho Lee"],"abstract":"Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed that while additional fine-tuning of the zero-shot model on the reference data results in enhanced downstream performance, it compromises the model's robustness against distribution shifts. Our investigation begins by examining the conditions required to achieve the goals of robust fine-tuning, employing descriptions based on feature distortion theory and joint energy-based models. Subsequently, we propose a novel robust fine-tuning algorithm, Lipsum-FT, that effectively utilizes the language modeling aspect of the vision-language pre-trained models. Extensive experiments conducted on distribution shift scenarios in DomainNet and ImageNet confirm the superiority of our proposed Lipsum-FT approach over existing robust fine-tuning methods.","url_abs":"https://arxiv.org/abs/2404.00860v1","url_pdf":"https://arxiv.org/pdf/2404.00860v1.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":"lipsum-ft-robust-fine-tuning-of-zero-shot","repo_url":"https://github.com/cs-giung/lipsum-ft","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.00860","atlas_url":"https://app.syntology.ai/?focus=2404.00860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00860"}},"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/cs-giung/lipsum-ft","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"b8e9ddb2c01d62ce","entry":"evaluate_acc","repo":"cs-giung/lipsum-ft","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/cs-giung/lipsum-ft/blob/HEAD/src/metrics.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":"b8e9ddb2c01d62ce"}},{"code_sha256_prefix":"366e435531a0708b","entry":"evaluate_nll","repo":"cs-giung/lipsum-ft","repo_kind":"official","path":"src/metrics.py","file_url":"https://github.com/cs-giung/lipsum-ft/blob/HEAD/src/metrics.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":"366e435531a0708b"}},{"code_sha256_prefix":"8ff2c6f4c7de8927","entry":"project_logits","repo":"cs-giung/lipsum-ft","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/cs-giung/lipsum-ft/blob/HEAD/src/data.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":"8ff2c6f4c7de8927"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}