{"type":"ScholarlyArticle","title":"CD^2: Constrained Dataset Distillation for Few-Shot Class-Incremental Learning","authors":[{"name":"Kexin Bao","slug":"kexin-bao","given":"Kexin","family":"Bao","affiliation":""},{"name":"Daichi Zhang","slug":"daichi-zhang","given":"Daichi","family":"Zhang","affiliation":""},{"name":"Hansong Zhang","slug":"hansong-zhang","given":"Hansong","family":"Zhang","affiliation":""},{"name":"Yong Li","slug":"yong-li","given":"Yong","family":"Li","affiliation":""},{"name":"Yutao Yue","slug":"yutao-yue","given":"Yutao","family":"Yue","affiliation":""},{"name":"Shiming Ge","slug":"shiming-ge","given":"Shiming","family":"Ge","affiliation":""}],"abstract":"Few-shot class-incremental learning (FSCIL) receives significant attention from the public to perform classification continuously with a few training samples, which suffers from the key catastrophic forgetting problem. Existing methods usually employ an external memory to store previous knowledge and treat it with incremental classes equally, which cannot properly preserve previous essential knowledge. To solve this problem and inspired by recent distillation works on knowledge transfer, we propose a framework termed Constrained Dataset Distillation (CD^2) to facilitate FSCIL, which includes a dataset distillation module (DDM) and a distillation constraint module (DCM). Specifically, the DDM synthesizes highly condensed samples guided by the classifier, forcing the model to learn compacted essential class-related clues from a few incremental samples. The DCM introduces a designed loss to constrain the previously learned class distribution, which can preserve distilled knowledge more sufficiently. Extensive experiments on three public datasets show the superiority of our method against other state-of-the-art competitors.","doi":"10.24963/ijcai.2025/530","url":"https://ijcai.org/proceedings/2025/530","pdf":"https://ijcai.org/proceedings/2025/0530.pdf","markdown":"https://ijcai.org/proceedings/2025/530.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/530","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":530,"pages":{"first":4761,"last":4769},"keywords":["Machine Learning: ML: Incremental learning","Machine Learning: ML: Few-shot learning","Computer Vision: CV: Recognition (object detection, categorization)","Computer Vision: CV: Image and video synthesis and generation"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}