{"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/adapter-merging-with-centroid-prototype","title":"Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning","arxiv_id":"2412.18219","date":"2024-12-24","proceeding":"CVPR 2025 1","authors":["Takuma Fukuda","Hiroshi Kera","Kazuhiko Kawamoto"],"abstract":"We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods trade-off between inference time and accuracy, ACMap consolidates task-specific adapters into a single adapter, ensuring constant inference time across tasks without compromising accuracy. The framework employs adapter merging to build a shared subspace that aligns task representations and mitigates forgetting, while centroid prototype mapping maintains high accuracy through consistent adaptation in the shared subspace. To further improve scalability, an early stopping strategy limits adapter merging as tasks increase. Extensive experiments on five benchmark datasets demonstrate that ACMap matches state-of-the-art accuracy while maintaining inference time comparable to the fastest existing methods. The code is available at https://github.com/tf63/ACMap","url_abs":"https://arxiv.org/abs/2412.18219v1","url_pdf":"https://arxiv.org/pdf/2412.18219v1.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":"adapter-merging-with-centroid-prototype","repo_url":"https://github.com/tf63/acmap","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":"exemplar-free","task_name":"Exemplar-Free"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"},{"method_slug":"early-stopping","method_name":"Early Stopping"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.18219","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}