{"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/few-shot-learner-parameterization-by","title":"Few-shot Learner Parameterization by Diffusion Time-steps","arxiv_id":"2403.02649","date":"2024-03-05","proceeding":"CVPR 2024 1","authors":["Zhongqi Yue","Pan Zhou","Richang Hong","Hanwang Zhang","Qianru Sun"],"abstract":"Even when using large multi-modal foundation models, few-shot learning is still challenging -- if there is no proper inductive bias, it is nearly impossible to keep the nuanced class attributes while removing the visually prominent attributes that spuriously correlate with class labels. To this end, we find an inductive bias that the time-steps of a Diffusion Model (DM) can isolate the nuanced class attributes, i.e., as the forward diffusion adds noise to an image at each time-step, nuanced attributes are usually lost at an earlier time-step than the spurious attributes that are visually prominent. Building on this, we propose Time-step Few-shot (TiF) learner. We train class-specific low-rank adapters for a text-conditioned DM to make up for the lost attributes, such that images can be accurately reconstructed from their noisy ones given a prompt. Hence, at a small time-step, the adapter and prompt are essentially a parameterization of only the nuanced class attributes. For a test image, we can use the parameterization to only extract the nuanced class attributes for classification. TiF learner significantly outperforms OpenCLIP and its adapters on a variety of fine-grained and customized few-shot learning tasks. Codes are in https://github.com/yue-zhongqi/tif.","url_abs":"https://arxiv.org/abs/2403.02649v2","url_pdf":"https://arxiv.org/pdf/2403.02649v2.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":"few-shot-learner-parameterization-by","repo_url":"https://github.com/yue-zhongqi/tif","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.02649","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02649"}},"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":"deterministic:regex_extraction","url":"https://github.com/yue-zhongqi/tif","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"95fcd8931dd047dc","entry":"classwise_acc","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/utils.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"95fcd8931dd047dc"}},{"code_sha256_prefix":"d4ddb26ae6d1b327","entry":"classwise_accuracy_for_list","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/utils.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4ddb26ae6d1b327"}},{"code_sha256_prefix":"abbf4d1dc2d132fd","entry":"get_display_images","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/utils_dreambooth_lora.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/utils_dreambooth_lora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"abbf4d1dc2d132fd"}},{"code_sha256_prefix":"c1002c651e108147","entry":"get_scheduler_config","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/utils_diffusion.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/utils_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c1002c651e108147"}},{"code_sha256_prefix":"ac4ec1f65f41eb38","entry":"get_transform","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/diffusion_classifier.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/diffusion_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ac4ec1f65f41eb38"}},{"code_sha256_prefix":"0061b82d026cd6db","entry":"make_grid","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/utils_dreambooth_lora.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/utils_dreambooth_lora.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0061b82d026cd6db"}},{"code_sha256_prefix":"9e8ac1cb3c9bd571","entry":"cls_acc","repo":"yue-zhongqi/tif","repo_kind":"official","path":"inference/methods/utils.py","file_url":"https://github.com/yue-zhongqi/tif/blob/HEAD/inference/methods/utils.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":"9e8ac1cb3c9bd571"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}