{"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/unleashing-the-power-of-meta-tuning-for-few","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","arxiv_id":"2403.08477","date":"2024-03-13","proceeding":null,"authors":["Shengzhuang Chen","Jihoon Tack","Yunqiao Yang","Yee Whye Teh","Jonathan Richard Schwarz","Ying WEI"],"abstract":"Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of alternatives such as meta-learning. In trying to harness the best of both worlds, meta-tuning introduces a subsequent optimization stage of foundation models but has so far only shown limited success and crucially tends to underperform on out-of-distribution (OOD) tasks. In this paper, we introduce Sparse MetA-Tuning (SMAT), a method inspired by sparse mixture-of-experts approaches and trained to isolate subsets of pre-trained parameters automatically for meta-tuning on each task. SMAT successfully overcomes OOD sensitivity and delivers on the promise of enhancing the transfer abilities of vision foundation models beyond parameter-efficient fine-tuning. We establish new state-of-the-art results on a challenging combination of Meta-Dataset augmented with additional OOD tasks in both zero-shot and gradient-based adaptation settings. In addition, we provide a thorough analysis of the superiority of learned over hand-designed sparsity patterns for sparse expert methods and the pivotal importance of the sparsity level in balancing between in-distribution and out-of-distribution generalization. Our code is publicly available.","url_abs":"https://arxiv.org/abs/2403.08477v3","url_pdf":"https://arxiv.org/pdf/2403.08477v3.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":"unleashing-the-power-of-meta-tuning-for-few","repo_url":"https://github.com/szc12153/sparse_meta_tuning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-meta-dataset","task":"Few-Shot Image Classification","dataset":"Meta-Dataset","model":"SMAT (DINO-VIT-Base-16-224)","rank_in_archive_order":1,"of":22,"metrics":{"Accuracy":"85.27"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.08477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08477"}},"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/szc12153/sparse_meta_tuning","reach":{"status":"ok"}}],"summary":{"ran":7},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":"f22f9e770e3f12c4","entry":"collapse","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.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":"f22f9e770e3f12c4"}},{"code_sha256_prefix":"286b18e3571ee47f","entry":"compute_num_query","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/sampling.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/sampling.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":"286b18e3571ee47f"}},{"code_sha256_prefix":"3df50298a5193115","entry":"get_ancestors","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.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":"3df50298a5193115"}},{"code_sha256_prefix":"ad5021d14e809d40","entry":"get_node_ancestors","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/imagenet_specification.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":"ad5021d14e809d40"}},{"code_sha256_prefix":"39723338c82449eb","entry":"get_total_images_per_class","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/dataset_spec.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/dataset_spec.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":"39723338c82449eb"}},{"code_sha256_prefix":"2cd79f76eda06a94","entry":"sample_class_ids_uniformly","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/sampling.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/sampling.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":"2cd79f76eda06a94"}},{"code_sha256_prefix":"fcf48305474e4aa6","entry":"sample_num_ways_uniformly","repo":"szc12153/sparse_meta_tuning","repo_kind":"official","path":"src/taskdatasets/meta_dataset/meta_dataset/sampling.py","file_url":"https://github.com/szc12153/sparse_meta_tuning/blob/HEAD/src/taskdatasets/meta_dataset/meta_dataset/sampling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fcf48305474e4aa6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}