{"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-recognition-via-stage-wise-augmented","title":"Few-Shot Recognition via Stage-Wise Retrieval-Augmented Finetuning","arxiv_id":"2406.11148","date":"2024-06-17","proceeding":"CVPR 2025 1","authors":["Tian Liu","Huixin Zhang","Shubham Parashar","Shu Kong"],"abstract":"Few-shot recognition (FSR) aims to train a classification model with only a few labeled examples of each concept concerned by a downstream task, where data annotation cost can be prohibitively high. We develop methods to solve FSR by leveraging a pretrained Vision-Language Model (VLM). We particularly explore retrieval-augmented learning (RAL), which retrieves data from the VLM's pretraining set to learn better models for serving downstream tasks. RAL has been widely studied in zero-shot recognition but remains under-explored in FSR. Although applying RAL to FSR may seem straightforward, we observe interesting and novel challenges and opportunities. First, somewhat surprisingly, finetuning a VLM on a large amount of retrieved data underperforms state-of-the-art zero-shot methods. This is due to the imbalanced distribution of retrieved data and its domain gaps with the few-shot examples in the downstream task. Second, more surprisingly, we find that simply finetuning a VLM solely on few-shot examples significantly outperforms previous FSR methods, and finetuning on the mix of retrieved and few-shot data yields even better results. Third, to mitigate the imbalanced distribution and domain gap issues, we propose Stage-Wise retrieval-Augmented fineTuning (SWAT), which involves end-to-end finetuning on mixed data in the first stage and retraining the classifier on the few-shot data in the second stage. Extensive experiments on nine popular benchmarks demonstrate that SWAT significantly outperforms previous methods by $>$6% accuracy.","url_abs":"https://arxiv.org/abs/2406.11148v2","url_pdf":"https://arxiv.org/pdf/2406.11148v2.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-recognition-via-stage-wise-augmented","repo_url":"https://github.com/tian1327/swat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.11148","atlas_url":"https://app.syntology.ai/?focus=2406.11148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11148"}},"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/tian1327/swat","reach":{"status":"ok","spdx":"MIT"}}],"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":0,"samples":[{"code_sha256_prefix":"482ccec6fd43050d","entry":"calculate_scores","repo":"tian1327/swat","repo_kind":"official","path":"testing.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/testing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"482ccec6fd43050d"}},{"code_sha256_prefix":"2f7d382b8cb5b005","entry":"extract_mined_feats","repo":"tian1327/swat","repo_kind":"official","path":"retrieval/extract_mined_feature.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/retrieval/extract_mined_feature.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":"2f7d382b8cb5b005"}},{"code_sha256_prefix":"fdd19b3b01f3ecee","entry":"extract_mined_feats_batch","repo":"tian1327/swat","repo_kind":"official","path":"retrieval/extract_mined_feature.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/retrieval/extract_mined_feature.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":"fdd19b3b01f3ecee"}},{"code_sha256_prefix":"b43abf2d3deaa330","entry":"set_loss","repo":"tian1327/swat","repo_kind":"official","path":"utils/losses.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/utils/losses.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":"b43abf2d3deaa330"}},{"code_sha256_prefix":"d825b8ba56586c53","entry":"validate_dataset","repo":"tian1327/swat","repo_kind":"official","path":"testing.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/testing.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":"d825b8ba56586c53"}},{"code_sha256_prefix":"2c79cde83ec23919","entry":"validate_multitask","repo":"tian1327/swat","repo_kind":"official","path":"testing.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/testing.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":"2c79cde83ec23919"}},{"code_sha256_prefix":"5a340cb616c813ca","entry":"extract_test_feats","repo":"tian1327/swat","repo_kind":"official","path":"retrieval/extract_mined_feature.py","file_url":"https://github.com/tian1327/swat/blob/HEAD/retrieval/extract_mined_feature.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a340cb616c813ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}