# Neural Prior Estimation: Learning Class Priors from Latent Representations Source: [Neural Prior Estimation: Learning Class Priors from Latent Representations]() Collection index: [llms.txt]() Data updated: 2026-02-24T05:00:04.779Z Authors: Masoud Yavari, Payman Moallem Published: 2026-02-19T21:36:34.000Z ## Abstract Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the Neural Prior Estimator (NPE), a framework that learns feature-conditioned log-prior estimates from latent representations. NPE employs one or more Prior Estimation Modules trained jointly with the backbone via a one-way logistic loss. Under the Neural Collapse regime, NPE is analytically shown to recover the class log-prior up to an additive constant, providing a theoretically grounded adaptive signal without requiring explicit class counts or distribution-specific hyperparameters. The learned estimate is incorporated into logit adjustment, forming NPE-LA, a principled mechanism for bias-aware prediction. Experiments on long-tailed CIFAR and imbalanced semantic segmentation benchmarks (STARE, ADE20K) demonstrate consistent improvements, particularly for underrepresented classes. NPE thus offers a lightweight and theoretically justified approach to learned prior estimation and imbalance-aware prediction. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on CIFAR-100 long-tailed (test) (Specific Imbalance Accuracy)](): Image Classification; CIFAR-100 Long-Tailed (test); Top-1 Acc (rho=200): 43.96. - [Semantic Segmentation on ADE20K (val)](): Semantic segmentation; ADE20K (val); mIoU: 44.73. - [Image Classification on CIFAR-10 long-tailed (test)](): Image Classification; CIFAR-10 long-tailed (test); Top-1 Acc: not recorded. ## Original sources and implementation [Original paper]() [PDF]()