发表机构
Meijo University（名城大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对长尾类增量学习，提出无需新增可学习参数的NeuroGuard方法，通过AGS、CRK、FBE三个组件控制梯度更新，在5种LT-CIL设置及4项基准对比中均提升了DGR的性能。
AI 中文摘要
长尾类增量学习（LT-CIL）需从不平衡数据流中学习新类，同时保留旧类。现有方法主要针对重放、分类器或损失函数进行改进，本研究关注另一关键因素：在每个任务边界处特征表征应被更新的强度。我们提出NeuroGuard，一种添加至基于重放的LT-CIL基线方法DGR的更新控制方法，无需新增可学习参数，且保留DGR的重放记忆、分类器及损失项集合。该方法包含三个核心组件：自适应梯度缩放（AGS）将教师模型的不确定性转换为针对单个任务的梯度缩放系数；置信度排序知识蒸馏重加权（CRK）为教师模型预测置信度较低的重放样本分配更大的知识蒸馏权重；脆弱性融合熵门（FBE）将旧记忆泄漏信息纳入缩放系数的决策过程。在5种LT-CIL设置中，NeuroGuard在所有设置下均优于DGR；在4项主要基准对比中，其达到了对比方法中最优的任务无关准确率，且旧类与新类准确率均有提升，5种设置下中频类准确率均持续改善。控制对比实验表明，该性能提升并非源于通用梯度抑制：AGS在全部5种设置下均优于匹配的固定缩放对照，证明任务边界特定的梯度缩放比在整个学习过程中应用相同平均缩放系数更有效。
英文摘要
Long-tailed class-incremental learning (LT-CIL) must learn new classes from imbalanced streams while retaining old classes. Existing methods mainly change replay, classifiers, or losses. We study a different factor, namely how strongly the feature representation should be updated at each task boundary. We propose NeuroGuard, an update-control method added to DGR, a replay-based LT-CIL baseline, without adding learnable parameters. NeuroGuard preserves DGR's replay memory, classifier, and set of loss terms. Adaptive Gradient Scaling (AGS) converts teacher uncertainty into one task-wise gradient scale. Confidence-Ranked Knowledge Distillation Reweighting (CRK) gives larger knowledge-distillation weights to replay samples that the teacher predicts less decisively. Fragility-Blended Entropy Gate (FBE) adds old-memory leakage to the scale decision. Across five LT-CIL settings, NeuroGuard improves over DGR in every setting. In the four main benchmark comparisons, it achieves the best task-agnostic accuracy among the compared methods. The gains extend to both old- and new-class accuracy, while medium-frequency accuracy improves consistently across all five settings. Controlled comparisons show that the gain does not come from generic gradient suppression: AGS outperforms a matched fixed-scale control in all five settings, demonstrating that boundary-specific scaling is more effective than applying the same average scale throughout learning.
CommentsAccepted at HCV workshop on ECCV2026
