发表机构
CICATA Querétaro Instituto Politecnico Nacional; Facultad de Informática Universidad Autónoma de Querétaro; Escuela Nacional de Estudios Superiores Universidad Nacional Autónoma de México（国立理工学院克雷塔罗中心研究与高级研究中心; 克雷塔罗自治大学信息学院; 国立自治大学高等研究学校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究长尾识别中仅再训练分类器能否减少尾部误差，提出BS - cRT方法，在多个数据集上实验，该方法持续提高少样本准确率，还分析了CBRM的失败模式，支持BS - cRT为实用基线，表明边界监督需考虑类频率。
AI 中文摘要
长尾识别方法通常会修改损失、边界或表示以减少频繁类别的主导。本文探讨在平衡软最大化训练后，仅通过再训练分类器能否减少剩余的尾部误差。评估了BS - cRT，它先使用平衡软最大化训练骨干网络和余弦分类器，冻结骨干网络，然后仅在平衡情节批次上更新分类器。实验表明，在多个数据集上，这种仅分类器步骤持续提高了少样本准确率。同时分析了反事实边界风险最小化（CBRM）的两种失败模式。结果支持BS - cRT作为实用的分类器端基线，并表明边界监督必须考虑类频率。
英文摘要
Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes. We ask whether, after Balanced Softmax training, the remaining tail error can be reduced by retraining only the classifier. We evaluate BS-cRT, a two-stage procedure that trains a backbone and cosine classifier with Balanced Softmax, freezes the backbone, and updates only the classifier on balanced episodic batches. The second stage keeps the empirical-prior Balanced Softmax objective and uses raw cosine logits at inference. Across CIFAR-100-LT, CIFAR-10-LT, ImageNet-LT, and Places-LT, this classifier-only step consistently improves Few-shot accuracy over the matched Balanced Softmax checkpoint. At imbalance factor 100, Few-shot gains are +5.15 points on CIFAR-100-LT and +5.83 on CIFAR-10-LT; on ImageNet-LT and Places-LT, gains are +6.92 and +9.78 points, respectively, with a Top-1/Few-shot trade-off on ImageNet-LT. We also analyze Counterfactual Boundary Risk Minimization (CBRM), a boundary-probe extension using prototype-based features near decision boundaries. CBRM identifies two failure modes: scaled-logit cosine margins destabilize training, and corrected hardest-negative probes remain head-class anchored. The results support BS-cRT as a practical classifier-side baseline and indicate that boundary supervision must account for class frequency.
Comments18 pages, 6 figures, 7 tables
