提出按类别评估专家可信度的集成方法，提升长尾分类中稀有类表现。
CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classification
- 通过阈值结构采样生成多样化专家，保留完整标签空间。
- 用平滑类精度估计每类专家可信度，实现精准加权融合。
- 适合关注稀有类别性能、需可靠集成模型的研究者使用。
长尾分类因数据分布不均导致模型在常见类与稀有类上的可靠性差异大。现有方法虽通过重平衡、调整、表征学习或多专家建模缓解此问题，却很少评估各专家对不同类别的可信度。本文提出CLEAR（Class-wise reLiability-aware Expert Aggregation for long-tailed Recognition），一种模块化集成框架：通过阈值结构采样生成多样专家并保留全标签空间；利用平滑类精度公式估计每个专家在各类别上的可信度得分；推理时采用类级别广义乘积-专家融合策略，使不同专家在不同类别上被差异化强调。在CIFAR-100-LT、ImageNet-LT和Places-LT多个基准上，无论使用何种骨干网络，CLEAR均取得具有竞争力的整体准确率，并在少数样本类别上表现尤为突出，验证了类级别专家可信度作为长尾集成学习设计原则的有效性。
原文摘要 · Abstract (English)
Long-tailed classification poses a reliability challenge because models trained on imbalanced data are unevenly reliable across frequent and underrepresented classes. While existing methods address imbalance through re-balancing, adjustment, representation learning, or multi-expert modeling, they rarely estimate which expert should be trusted for each class. This paper proposes CLEAR (Class-wise reLiability-aware Expert Aggregation for long-tailed Recognition), a modular ensemble framework for long-tailed classification. CLEAR generates diverse experts through threshold-based structured sampling while preserving the full label space, then estimates a class-wise trust score for each expert using a smoothed class-wise precision formulation. During inference, expert predictions are combined through class-wise generalized product-of-experts aggregation, allowing different experts to be emphasized for different classes. Experiments on CIFAR-100-LT, ImageNet-LT, and Places-LT across multiple backbones show that CLEAR achieves competitive overall accuracy and particularly strong few-shot performance. These results support class-wise expert reliability as a useful design principle for long-tailed ensemble learning.
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。