{"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/calibrating-higher-order-statistics-for-few","title":"Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained Vision Transformers","arxiv_id":"2404.06622","date":"2024-04-09","proceeding":null,"authors":["Dipam Goswami","Bartłomiej Twardowski","Joost Van de Weijer"],"abstract":"Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in many-shot CIL (MSCIL) (using all available training data) exploited pre-trained models to reduce forgetting and achieve better plasticity. In a similar fashion, we use ViT models pre-trained on large-scale datasets for few-shot settings, which face the critical issue of low plasticity. FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards. While the focus of most recent studies is on how to learn the many-shot first task so that the model generalizes to all future few-shot tasks, we explore in this work how to better model the few-shot data using pre-trained models, irrespective of how the first task is trained. Inspired by recent works in MSCIL, we explore how using higher-order feature statistics can influence the classification of few-shot classes. We identify the main challenge of obtaining a good covariance matrix from few-shot data and propose to calibrate the covariance matrix for new classes based on semantic similarity to the many-shot base classes. Using the calibrated feature statistics in combination with existing methods significantly improves few-shot continual classification on several FSCIL benchmarks. Code is available at https://github.com/dipamgoswami/FSCIL-Calibration.","url_abs":"https://arxiv.org/abs/2404.06622v1","url_pdf":"https://arxiv.org/pdf/2404.06622v1.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":"calibrating-higher-order-statistics-for-few","repo_url":"https://github.com/dipamgoswami/fscil-calibration","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":"few-shot-class-incremental-learning","task_name":"Few-Shot Class-Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.06622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06622"}},"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/dipamgoswami/fscil-calibration","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_honours":2,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":15,"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":"d9def42110729a85","entry":"conv1x1","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"backbone/resnet.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/backbone/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"backbone/resnet.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/backbone/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"6bdbe3d6368c4cde","entry":"count_parameters","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/toolkit.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/toolkit.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bdbe3d6368c4cde"}},{"code_sha256_prefix":"4072283c98270784","entry":"reduce_proxies","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"backbone/linears.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/backbone/linears.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4072283c98270784"}},{"code_sha256_prefix":"284e2e0345abe291","entry":"target2onehot","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/toolkit.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/toolkit.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"284e2e0345abe291"}},{"code_sha256_prefix":"929c76a2fa2e8c42","entry":"tensor2numpy","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/toolkit.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/toolkit.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"929c76a2fa2e8c42"}},{"code_sha256_prefix":"cf462ad7948ff43b","entry":"accimage_loader","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/data_manager.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/data_manager.py","link_basis":"harvester_set","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":"cf462ad7948ff43b"}},{"code_sha256_prefix":"b620954495190c1a","entry":"build_transform","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/data.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/data.py","link_basis":"harvester_set","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":"b620954495190c1a"}},{"code_sha256_prefix":"2c9953e20558c977","entry":"default_loader","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/data_manager.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/data_manager.py","link_basis":"harvester_set","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":"2c9953e20558c977"}},{"code_sha256_prefix":"cebcd10bc5d204d3","entry":"get_backbone","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/inc_net.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/inc_net.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":"cebcd10bc5d204d3"}},{"code_sha256_prefix":"e6737521b2cde29c","entry":"get_model","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/factory.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/factory.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":"e6737521b2cde29c"}},{"code_sha256_prefix":"66b63ed4f327a712","entry":"pil_loader","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"utils/data_manager.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/utils/data_manager.py","link_basis":"harvester_set","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":"66b63ed4f327a712"}},{"code_sha256_prefix":"1b21828124579725","entry":"resnet18","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"backbone/resnet.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/backbone/resnet.py","link_basis":"harvester_set","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":"1b21828124579725"}},{"code_sha256_prefix":"da00da4b8fae8fe5","entry":"vit_base_patch16_224_adapter","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"backbone/vision_transformer_adapter.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/backbone/vision_transformer_adapter.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":"da00da4b8fae8fe5"}},{"code_sha256_prefix":"9ed8a1105d420fac","entry":"vit_base_patch16_224_in21k_adapter","repo":"dipamgoswami/fscil-calibration","repo_kind":"official","path":"backbone/vision_transformer_adapter.py","file_url":"https://github.com/dipamgoswami/fscil-calibration/blob/HEAD/backbone/vision_transformer_adapter.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":"9ed8a1105d420fac"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}