{"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-tuning-of-foundation-models-for","title":"Few-shot Tuning of Foundation Models for Class-incremental Learning","arxiv_id":"2405.16625","date":"2024-05-26","proceeding":null,"authors":["Shuvendu Roy","Elham Dolatabadi","Arash Afkanpour","Ali Etemad"],"abstract":"For the first time, we explore few-shot tuning of vision foundation models for class-incremental learning. Unlike existing few-shot class incremental learning (FSCIL) methods, which train an encoder on a base session to ensure forward compatibility for future continual learning, foundation models are generally trained on large unlabelled data without such considerations. This renders prior methods from traditional FSCIL incompatible for FSCIL with the foundation model. To this end, we propose Consistency-guided Asynchronous Contrastive Tuning (CoACT), a new approach to continually tune foundation models for new classes in few-shot settings. CoACT comprises three components: (i) asynchronous contrastive tuning, which learns new classes by including LoRA modules in the pre-trained encoder, while enforcing consistency between two asynchronous encoders; (ii) controlled fine-tuning, which facilitates effective tuning of a subset of the foundation model; and (iii) consistency-guided incremental tuning, which enforces additional regularization during later sessions to reduce forgetting of the learned classes. We perform an extensive study on 16 diverse datasets and demonstrate the effectiveness of CoACT, outperforming the best baseline method by 2.47% on average and with up to 12.52% on individual datasets. Additionally, CoACT shows reduced forgetting and robustness in low-shot experiments. As an added bonus, CoACT shows up to 13.5% improvement in standard FSCIL over the current SOTA on benchmark evaluations. We make our code publicly available at https://github.com/ShuvenduRoy/CoACT-FSCIL.","url_abs":"https://arxiv.org/abs/2405.16625v1","url_pdf":"https://arxiv.org/pdf/2405.16625v1.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-tuning-of-foundation-models-for","repo_url":"https://github.com/shuvenduroy/coact-fscil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"few-shot-class-incremental-learning","task_name":"Few-Shot Class-Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-class-incremental-learning-on-cifar","task":"Few-Shot Class-Incremental Learning","dataset":"CIFAR-100","model":"CoACT","rank_in_archive_order":2,"of":11,"metrics":{"Last Accuracy":"84.63"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-class-incremental-learning-on-cub","task":"Few-Shot Class-Incremental Learning","dataset":"CUB-200-2011","model":"CoACT","rank_in_archive_order":1,"of":6,"metrics":{"Last Accuracy ":"81.19"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-class-incremental-learning-on-mini","task":"Few-Shot Class-Incremental Learning","dataset":"mini-Imagenet","model":"CoACT","rank_in_archive_order":1,"of":12,"metrics":{"Last Accuracy ":"96.24"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.16625","atlas_url":"https://app.syntology.ai/?focus=2405.16625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16625"}},"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/shuvenduroy/coact-fscil","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":4},"by_repo_kind":{"official":{"samples":10,"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":"63025523d2abf626","entry":"get_few_shot_samples_indices_per_class","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"dataloaders/utils.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/dataloaders/utils.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":"63025523d2abf626"}},{"code_sha256_prefix":"de7c95a0e22002e9","entry":"get_model_args","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"models/model_utils.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/models/model_utils.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":"de7c95a0e22002e9"}},{"code_sha256_prefix":"dc4c55b2bb7e61f7","entry":"get_optimizer_base","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"methods/helper.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/methods/helper.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":"dc4c55b2bb7e61f7"}},{"code_sha256_prefix":"a15a9f5297aabec5","entry":"get_session_classes","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"dataloaders/utils.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/dataloaders/utils.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":"a15a9f5297aabec5"}},{"code_sha256_prefix":"6f0eb419e44fffcf","entry":"override_training_configs","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"utils/train_utils.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/utils/train_utils.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":"6f0eb419e44fffcf"}},{"code_sha256_prefix":"bba3a1320c12ccd7","entry":"str2bool","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"utils/train_utils.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/utils/train_utils.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":"bba3a1320c12ccd7"}},{"code_sha256_prefix":"8b95e799ab827c9c","entry":"count_acc","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"methods/helper.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/methods/helper.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":"8b95e799ab827c9c"}},{"code_sha256_prefix":"0568a7c52850965e","entry":"get_hf_data","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"dataloaders/datasets/hf_dataset.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/dataloaders/datasets/hf_dataset.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":"0568a7c52850965e"}},{"code_sha256_prefix":"efe02552f3ea842a","entry":"get_transform","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"dataloaders/helpter.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/dataloaders/helpter.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":"efe02552f3ea842a"}},{"code_sha256_prefix":"4d2b757d67335855","entry":"test","repo":"shuvenduroy/coact-fscil","repo_kind":"official","path":"methods/helper.py","file_url":"https://github.com/shuvenduroy/coact-fscil/blob/HEAD/methods/helper.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":"4d2b757d67335855"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}