{"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/constrained-few-shot-class-incremental","title":"Constrained Few-shot Class-incremental Learning","arxiv_id":"2203.16588","date":"2022-03-30","proceeding":"CVPR 2022 1","authors":["Michael Hersche","Geethan Karunaratne","Giovanni Cherubini","Luca Benini","Abu Sebastian","Abbas Rahimi"],"abstract":"Continually learning new classes from fresh data without forgetting previous knowledge of old classes is a very challenging research problem. Moreover, it is imperative that such learning must respect certain memory and computational constraints such as (i) training samples are limited to only a few per class, (ii) the computational cost of learning a novel class remains constant, and (iii) the memory footprint of the model grows at most linearly with the number of classes observed. To meet the above constraints, we propose C-FSCIL, which is architecturally composed of a frozen meta-learned feature extractor, a trainable fixed-size fully connected layer, and a rewritable dynamically growing memory that stores as many vectors as the number of encountered classes. C-FSCIL provides three update modes that offer a trade-off between accuracy and compute-memory cost of learning novel classes. C-FSCIL exploits hyperdimensional embedding that allows to continually express many more classes than the fixed dimensions in the vector space, with minimal interference. The quality of class vector representations is further improved by aligning them quasi-orthogonally to each other by means of novel loss functions. Experiments on the CIFAR100, miniImageNet, and Omniglot datasets show that C-FSCIL outperforms the baselines with remarkable accuracy and compression. It also scales up to the largest problem size ever tried in this few-shot setting by learning 423 novel classes on top of 1200 base classes with less than 1.6% accuracy drop. Our code is available at https://github.com/IBM/constrained-FSCIL.","url_abs":"https://arxiv.org/abs/2203.16588v1","url_pdf":"https://arxiv.org/pdf/2203.16588v1.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":"constrained-few-shot-class-incremental","repo_url":"https://github.com/ibm/constrained-fscil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"constrained-few-shot-class-incremental","repo_url":"https://github.com/pulp-platform/fscil","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"class-incremental-learning-1","task_name":"class-incremental learning"},{"task_slug":null,"task_name":"continual few-shot 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":"C-FSCIL","rank_in_archive_order":8,"of":11,"metrics":{"Average Accuracy":"61.67","Last Accuracy":"50.47"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-class-incremental-learning-on-mini","task":"Few-Shot Class-Incremental Learning","dataset":"mini-Imagenet","model":"C-FSCIL","rank_in_archive_order":6,"of":12,"metrics":{"Average Accuracy":"61.61","Last Accuracy ":"51.41"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.16588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.16588"}},"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/pulp-platform/fscil","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ibm/constrained-fscil","reach":null}],"summary":{"ran":3,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":2,"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":0,"samples":[{"code_sha256_prefix":"023d83bdc1b890f6","entry":"FixedETFHead","repo":"pulp-platform/fscil","repo_kind":"listed","path":"code/lib/model.py","file_url":"https://github.com/pulp-platform/fscil/blob/HEAD/code/lib/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"023d83bdc1b890f6"}},{"code_sha256_prefix":"156432c471336c41","entry":"doubleexp_loss","repo":"ibm/constrained-fscil","repo_kind":"official","path":"code/lib/nudging.py","file_url":"https://github.com/ibm/constrained-fscil/blob/HEAD/code/lib/nudging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"156432c471336c41"}},{"code_sha256_prefix":"b37a590f53ff8c07","entry":"exp_loss","repo":"ibm/constrained-fscil","repo_kind":"official","path":"code/lib/nudging.py","file_url":"https://github.com/ibm/constrained-fscil/blob/HEAD/code/lib/nudging.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b37a590f53ff8c07"}},{"code_sha256_prefix":"dbde6f5f03d0551d","entry":"generate_random_orthogonal_matrix","repo":"pulp-platform/fscil","repo_kind":"listed","path":"code/lib/model.py","file_url":"https://github.com/pulp-platform/fscil/blob/HEAD/code/lib/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbde6f5f03d0551d"}},{"code_sha256_prefix":"04e206e207f1538c","entry":"nudging_model","repo":"ibm/constrained-fscil","repo_kind":"official","path":"code/lib/nudging.py","file_url":"https://github.com/ibm/constrained-fscil/blob/HEAD/code/lib/nudging.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04e206e207f1538c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}