{"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/on-the-test-time-zero-shot-generalization-of","title":"On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?","arxiv_id":"2405.02266","date":"2024-05-03","proceeding":"CVPR 2024 1","authors":["Maxime Zanella","Ismail Ben Ayed"],"abstract":"The development of large vision-language models, notably CLIP, has catalyzed research into effective adaptation techniques, with a particular focus on soft prompt tuning. Conjointly, test-time augmentation, which utilizes multiple augmented views of a single image to enhance zero-shot generalization, is emerging as a significant area of interest. This has predominantly directed research efforts toward test-time prompt tuning. In contrast, we introduce a robust MeanShift for Test-time Augmentation (MTA), which surpasses prompt-based methods without requiring this intensive training procedure. This positions MTA as an ideal solution for both standalone and API-based applications. Additionally, our method does not rely on ad hoc rules (e.g., confidence threshold) used in some previous test-time augmentation techniques to filter the augmented views. Instead, MTA incorporates a quality assessment variable for each view directly into its optimization process, termed as the inlierness score. This score is jointly optimized with a density mode seeking process, leading to an efficient training- and hyperparameter-free approach. We extensively benchmark our method on 15 datasets and demonstrate MTA's superiority and computational efficiency. Deployed easily as plug-and-play module on top of zero-shot models and state-of-the-art few-shot methods, MTA shows systematic and consistent improvements.","url_abs":"https://arxiv.org/abs/2405.02266v1","url_pdf":"https://arxiv.org/pdf/2405.02266v1.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":"on-the-test-time-zero-shot-generalization-of","repo_url":"https://github.com/maxzanella/mta","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"hoc","method_name":"HOC"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2405.02266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02266"}},"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/maxzanella/mta","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"abf7adc7e3aac64a","entry":"gaussian_kernel","repo":"maxzanella/mta","repo_kind":"official","path":"mta.py","file_url":"https://github.com/maxzanella/mta/blob/HEAD/mta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abf7adc7e3aac64a"}},{"code_sha256_prefix":"fc0e7e485d098d81","entry":"solve_mta","repo":"maxzanella/mta","repo_kind":"official","path":"mta.py","file_url":"https://github.com/maxzanella/mta/blob/HEAD/mta.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fc0e7e485d098d81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}