{"type":"ScholarlyArticle","title":"On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning","authors":[{"name":"Tianqi Wang","slug":"tianqi-wang","given":"Tianqi","family":"Wang","affiliation":""},{"name":"Jingcai Guo","slug":"jingcai-guo","given":"Jingcai","family":"Guo","affiliation":""},{"name":"Depeng Li","slug":"depeng-li","given":"Depeng","family":"Li","affiliation":""},{"name":"Zhi Chen","slug":"zhi-chen","given":"Zhi","family":"Chen","affiliation":""}],"abstract":"Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying any old class exemplars. An emerging theory-guided framework for CIL trains task-specific models for a shared network, shifting the pressure of forgetting to task-id prediction. In EF-CIL, task-id prediction is more challenging due to the lack of inter-task interaction (e.g., replays of exemplars). To address this issue, we conduct a theoretical analysis of the importance and feasibility of preserving a discriminative and consistent feature space, upon which we propose a novel method termed DCNet. Concretely, it progressively maps class representations into a hyperspherical space, in which different classes are orthogonally distributed to achieve ample inter-class separation. Meanwhile, it also introduces compensatory training to adaptively adjust supervision intensity, thereby aligning the degree of intra-class aggregation. Extensive experiments and theoretical analysis verified the superiority of DCNet. Code is available at https://github.com/Tianqi-Wang1/DCNet.","doi":"10.24963/ijcai.2025/715","url":"https://ijcai.org/proceedings/2025/715","pdf":"https://ijcai.org/proceedings/2025/0715.pdf","markdown":"https://ijcai.org/proceedings/2025/715.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/715","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":715,"pages":{"first":6424,"last":6432},"keywords":["Machine Learning: ML: Cost-sensitive learning","Machine Learning: ML: Incremental learning","Computer Vision: CV: Transfer, low-shot, semi- and un- supervised learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}