{"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/sus-x-training-free-name-only-transfer-of","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","arxiv_id":"2211.16198","date":"2022-11-28","proceeding":"ICCV 2023 1","authors":["Vishaal Udandarao","Ankush Gupta","Samuel Albanie"],"abstract":"Contrastive Language-Image Pre-training (CLIP) has emerged as a simple yet effective way to train large-scale vision-language models. CLIP demonstrates impressive zero-shot classification and retrieval on diverse downstream tasks. However, to leverage its full potential, fine-tuning still appears to be necessary. Fine-tuning the entire CLIP model can be resource-intensive and unstable. Moreover, recent methods that aim to circumvent this need for fine-tuning still require access to images from the target distribution. In this paper, we pursue a different approach and explore the regime of training-free \"name-only transfer\" in which the only knowledge we possess about the downstream task comprises the names of downstream target categories. We propose a novel method, SuS-X, consisting of two key building blocks -- SuS and TIP-X, that requires neither intensive fine-tuning nor costly labelled data. SuS-X achieves state-of-the-art zero-shot classification results on 19 benchmark datasets. We further show the utility of TIP-X in the training-free few-shot setting, where we again achieve state-of-the-art results over strong training-free baselines. Code is available at https://github.com/vishaal27/SuS-X.","url_abs":"https://arxiv.org/abs/2211.16198v4","url_pdf":"https://arxiv.org/pdf/2211.16198v4.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":"sus-x-training-free-name-only-transfer-of","repo_url":"https://github.com/vishaal27/sus-x","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sus-x-training-free-name-only-transfer-of","repo_url":"https://github.com/bethgelab/frequency_determines_performance","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.16198","atlas_url":"https://app.syntology.ai/?focus=2211.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16198"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vishaal27/sus-x","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bethgelab/frequency_determines_performance","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":3,"samples":[{"code_sha256_prefix":"25ffc80ee76ac3de","entry":"compute_image_text_distributions","repo":"vishaal27/sus-x","repo_kind":"official","path":"tipx.py","file_url":"https://github.com/vishaal27/sus-x/blob/HEAD/tipx.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25ffc80ee76ac3de"}},{"code_sha256_prefix":"eb3c01ddcd5d1e48","entry":"get_kl_divergence_sims","repo":"vishaal27/sus-x","repo_kind":"official","path":"tipx.py","file_url":"https://github.com/vishaal27/sus-x/blob/HEAD/tipx.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb3c01ddcd5d1e48"}},{"code_sha256_prefix":"27fec54e7b96961c","entry":"get_kl_div_sims","repo":"vishaal27/sus-x","repo_kind":"official","path":"tipx.py","file_url":"https://github.com/vishaal27/sus-x/blob/HEAD/tipx.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27fec54e7b96961c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}