arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.17853cs.LGcs.CV
收藏

神经先验估计:从潜在表示中学习类先验

Neural Prior Estimation: Learning Class Priors from Latent Representations

University of Isfahan(伊斯法罕大学);Department of Electrical Engineering Faculty of Engineering(电气工程系)

Masoud Yavari, Payman Moallem

AI总结:

本文提出神经先验估计器NPE,通过从潜在表示中学习类先验以缓解深度学习中的类别不平衡问题。

摘要:

类别不平衡会通过引入偏斜的有效类先验在深度神经网络中产生系统性偏差。本文引入了神经先验估计器(NPE),一种从潜在表示中学习特征条件对数先验估计的框架。NPE采用一个或多个先验估计模块,通过单向逻辑损失与主干网络联合训练。在神经崩溃 regime 下,NPE被证明可以解析地恢复类对数先验,直至加法常数,提供了一种理论支撑的自适应信号,而无需显式类计数或分布特定的超参数。所学的估计被纳入logit调整,形成NPE-LA,一种有原则的偏见意识预测机制。在长尾CIFAR和不平衡语义分割基准(STARE,ADE20K)上的实验显示了一致的改进,特别是在代表性不足的类别上。NPE因此提供了一种轻量且理论上合理的学习先验估计和不平衡意识预测的方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑