{"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/mamba-fscil-dynamic-adaptation-with-selective","title":"Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning","arxiv_id":"2407.06136","date":"2024-07-08","proceeding":null,"authors":["Xiaojie Li","Yibo Yang","Jianlong Wu","Bernard Ghanem","Liqiang Nie","Min Zhang"],"abstract":"Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples while preserving the knowledge of previously learned classes. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially, prone to overfitting to the current session. Existing dynamic strategies require the expansion of the parameter space continually, leading to increased complexity. In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL, leveraging its dynamic weights and strong ability in sequence modeling to address these challenges. Concretely, we propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation. The dual design enables the model to maintain the robust features of base classes, while adaptively learning distinctive feature shifts for novel classes. Additionally, we develop a class-sensitive selective scan mechanism to guide dynamic adaptation. It minimizes the disruption to base-class representations caused by training on novel data, and meanwhile, forces the selective scan to perform in distinct patterns between base and novel classes. Experiments on miniImageNet, CUB-200, and CIFAR-100 demonstrate that our framework outperforms the existing state-of-the-art methods. The code is available at \\url{https://github.com/xiaojieli0903/Mamba-FSCIL}.","url_abs":"https://arxiv.org/abs/2407.06136v2","url_pdf":"https://arxiv.org/pdf/2407.06136v2.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":"mamba-fscil-dynamic-adaptation-with-selective","repo_url":"https://github.com/xiaojieli0903/mamba-fscil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental 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":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.06136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06136"}},"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/xiaojieli0903/mamba-fscil","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"official":{"samples":8,"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":8,"samples":[{"code_sha256_prefix":"742767e6f63f427e","entry":"get_test_loader_cfg","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/apis/fscil.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/apis/fscil.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":"742767e6f63f427e"}},{"code_sha256_prefix":"ba7b868fec181b57","entry":"selective_scan_ref","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/models/mamba_ssm/ops/selective_scan_interface.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/models/mamba_ssm/ops/selective_scan_interface.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba7b868fec181b57"}},{"code_sha256_prefix":"eda7b73324d5e67e","entry":"decode","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/models/mamba_ssm/utils/generation.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/models/mamba_ssm/utils/generation.py","link_basis":"harvester_set","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":"eda7b73324d5e67e"}},{"code_sha256_prefix":"9a2b14ec4b86cf17","entry":"load_config_hf","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/models/mamba_ssm/utils/hf.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/models/mamba_ssm/utils/hf.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":"9a2b14ec4b86cf17"}},{"code_sha256_prefix":"68da9135cb5a5473","entry":"load_state_dict_hf","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/models/mamba_ssm/utils/hf.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/models/mamba_ssm/utils/hf.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":"68da9135cb5a5473"}},{"code_sha256_prefix":"da95e9a7906f3d52","entry":"modify_logit_for_repetition_penalty","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/models/mamba_ssm/utils/generation.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/models/mamba_ssm/utils/generation.py","link_basis":"harvester_set","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":"da95e9a7906f3d52"}},{"code_sha256_prefix":"1dd5c9c714460567","entry":"parse_losses","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/apis/fscil.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/apis/fscil.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":"1dd5c9c714460567"}},{"code_sha256_prefix":"8eafd3cf90152c82","entry":"sample","repo":"xiaojieli0903/mamba-fscil","repo_kind":"official","path":"mmfscil/models/mamba_ssm/utils/generation.py","file_url":"https://github.com/xiaojieli0903/mamba-fscil/blob/HEAD/mmfscil/models/mamba_ssm/utils/generation.py","link_basis":"harvester_set","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":"8eafd3cf90152c82"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}