{"ID":2866292,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.19664","arxiv_id":"2509.19664","title":"MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning","abstract":"Few-Shot Class-Incremental Learning (FSCIL) must contend with the dual challenge of learning new classes from scarce samples while preserving old class knowledge. Existing methods use the frozen feature extractor and class-averaged prototypes to mitigate against catastrophic forgetting and overfitting. However, new-class prototypes suffer significant estimation bias due to extreme data scarcity, whereas base-class prototypes benefit from sufficient data. In this work, we theoretically demonstrate that aligning the new-class priors with old-class statistics via Bayesian analysis reduces variance and improves prototype accuracy. Furthermore, we propose large-scale contrastive learning to enforce cross-category feature tightness. To further enrich feature diversity and inject prior information for new-class prototypes, we integrate momentum self-supervision and virtual categories into the Momentum Tightness and Contrast framework (MoTiC), constructing a feature space with rich representations and enhanced interclass cohesion. Experiments on three FSCIL benchmarks produce state-of-the-art performances, particularly on the fine-grained task CUB-200, validating our method's ability to reduce estimation bias and improve incremental learning robustness.","short_abstract":"Few-Shot Class-Incremental Learning (FSCIL) must contend with the dual challenge of learning new classes from scarce samples while preserving old class knowledge. Existing methods use the frozen feature extractor and class-averaged prototypes to mitigate against catastrophic forgetting and overfitting. However, new-cla...","url_abs":"https://arxiv.org/abs/2509.19664","url_pdf":"https://arxiv.org/pdf/2509.19664v1","authors":"[\"Zeyu He\",\"Shuai Huang\",\"Yuwu Lu\",\"Ming Zhao\"]","published":"2025-09-24T00:41:40Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}