{"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/12-mj-per-class-on-device-online-few-shot","title":"12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning","arxiv_id":"2403.07851","date":"2024-03-12","proceeding":null,"authors":["Yoga Esa Wibowo","Cristian Cioflan","Thorir Mar Ingolfsson","Michael Hersche","Leo Zhao","Abbas Rahimi","Luca Benini"],"abstract":"Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand their inference capabilities to new classes using only a few labeled examples, without forgetting the previously learned classes. Classical backpropagation-based learning and its variants are often unsuitable for battery-powered, memory-constrained systems at the extreme edge. In this work, we introduce Online Few-Shot Class-Incremental Learning (O-FSCIL), based on a lightweight model consisting of a pretrained and metalearned feature extractor and an expandable explicit memory storing the class prototypes. The architecture is pretrained with a novel feature orthogonality regularization and metalearned with a multi-margin loss. For learning a new class, our approach extends the explicit memory with novel class prototypes, while the remaining architecture is kept frozen. This allows learning previously unseen classes based on only a few examples with one single pass (hence online). O-FSCIL obtains an average accuracy of 68.62% on the FSCIL CIFAR100 benchmark, achieving state-of-the-art results. Tailored for ultra-low-power platforms, we implement O-FSCIL on the 60 mW GAP9 microcontroller, demonstrating online learning capabilities within just 12 mJ per new class.","url_abs":"https://arxiv.org/abs/2403.07851v1","url_pdf":"https://arxiv.org/pdf/2403.07851v1.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":"12-mj-per-class-on-device-online-few-shot","repo_url":"https://github.com/pulp-platform/fscil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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":"image-classification","task_name":"Image Classification"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-split-cifar-100","task":"Continual Learning","dataset":"split CIFAR-100","model":"OFSCIL","rank_in_archive_order":2,"of":2,"metrics":{"Average Accuracy":"68.62"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-split-cifar-100","task":"Image Classification","dataset":"split CIFAR-100","model":"OFSCIL","rank_in_archive_order":1,"of":2,"metrics":{"Average Accuracy":"68.62"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}