用网络隐空间学习类别先验，自动矫正长尾分布偏差
Neural Prior Estimation: Learning Class Priors from Latent Representations
- 在隐空间加轻量模块，通过坐标预测学类别频率信号
- 在CIFAR-10/100上提升少数类性能，优于交叉熵和cRT
- 可推广至密集预测任务，适合作为轻量校准工具
对数调整通过经验类别先验来纠正类别不平衡。我们研究是否可从网络表示中学习类似的类别频率信号，而无需显式提供类别计数。为此提出神经先验估计器（NPE），在隐表示上附加一个或多个轻量级先验估计模块（PEM）。每个PEM在真实坐标上使用单向逻辑回归目标进行训练，其输出具有频率依赖性，合并后形成NPE估计，用于学习对数调整，构成NPE-LA。在简化标量模型中，PEM目标的最优值随类别数单调递增，渐近增长如$\log N_c$，外加更慢的$\log \log N_c$项。在长尾的CIFAR-10和CIFAR-100上，NPE-LA表现与标准对数调整相当，并在报告设置下改善了少数类性能，优于交叉熵（CE）和校正训练（cRT）。在STARE和ADE20K上的实验进一步表明，该方法可作为密集预测任务的轻量级重新校准机制。
原文摘要 · Abstract (English)
Logit adjustment corrects class imbalance using the empirical class prior. We study whether a comparable class-frequency signal can instead be learned from the network representation, without explicitly supplying class counts to the correction rule. We introduce the Neural Prior Estimator (NPE), which attaches one or more lightweight Prior Estimation Modules (PEMs) to the latent representation. Each PEM is trained with a one-way logistic objective on the ground-truth coordinate. The resulting frequency-dependent outputs are combined into an NPE estimate and used as a learned logit correction, forming NPE-LA. In a simplified scalar model, the optimum of the PEM objective is monotone in the class count and grows asymptotically as $\log N_c$, up to a slower $\log \log N_c$ term. Experiments on long-tailed CIFAR-10 and CIFAR-100 show that NPE-LA is competitive with standard logit adjustment and improves minority-class performance over CE and cRT in the reported settings. Experiments on STARE and ADE20K further show that the same idea can be used as a lightweight recalibration mechanism for dense prediction.
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。