解决少样本增量学习中新类原型偏差问题，提升模型鲁棒性。
MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
- 基于贝叶斯分析对齐新旧类先验，降低原型估计偏差。
- 引入大规模对比学习增强类别间特征紧致性，提升分类精度。
- 融合动量自监督与虚拟类别，适合细粒度图像增量学习场景。
少样本增量学习（FSCIL）需在极少量新类样本下学习新知识，同时避免遗忘旧类。现有方法依赖冻结特征提取器和类别平均原型，但新类原型因数据极度稀缺存在显著估计偏差，而基础类原型则受益于充足数据。本文通过贝叶斯分析证明，将新类先验对齐旧类统计特性可降低方差、提升原型准确性。进一步提出大规模对比学习以增强跨类别特征紧致性。为丰富特征多样性并注入先验信息，将动量自监督与虚拟类别融入动量紧致性与对比框架（MoTiC），构建具有丰富表征和更强类间凝聚力的特征空间。在三个FSCIL基准上实验取得最优性能，尤其在细粒度任务CUB-200上表现突出，验证了该方法减少估计偏差和提升增量学习鲁棒性的能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。