paper-with-me

Papers

Prior Distribution and Model Confidence

2025-09-05 · Maksim Kazanskii, Artem Kasianov arxiv

We study how the training data distribution affects confidence and performance in image classification models. We introduce Embedding Density, a model-agnostic framework that estimates prediction confidence by measuring the distance of test samples from the training distribution in embedding space, without requiring retraining. By filtering low-density (low-confidence) predictions, our method significantly improves classification accuracy. We evaluate Embedding Density across multiple architectures and compare it with state-of-the-art out-of-distribution (OOD) detection methods. The proposed approach is potentially generalizable beyond computer vision.

📄 PDF Abstract BibTeX arXiv:2509.05485

Code (0)

등록된 구현이 없습니다.

Tasks

Image Classification

Similar Papers 제목 키워드 기반

On Prior Confidence and Belief Updating

2024-12-14 · Kenneth Chan, Gary Charness, Chetan Dave, J. Lucas Reddinger

We experimentally investigate how confidence over multiple priors affects belief updating. Theory predicts that the average Bayesian posterior is unaffected by confidence over multiple priors if average priors are the sa…

Believe Your Model: Distribution-Guided Confidence Calibration

2026-03-04 · Xizhong Yang, Haotian Zhang, Huiming Wang, Mofei Song arxiv

Large Reasoning Models have demonstrated remarkable performance with the advancement of test-time scaling techniques, which enhances prediction accuracy by generating multiple candidate responses and selecting the most r…

Answer Selection

Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means

2026-05-08 · Valentin Kilian, Stefano Cortinovis, François Caron arxiv

Confidence sequences based on test martingales provide time-uniform uncertainty quantification for the mean of bounded IID observations without parametric distributional assumptions. Their practical efficiency, however, …

Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling

2024-12-14 · Jinzong Dong, Zhaohui Jiang, Dong Pan, Haoyang Yu

Confidence calibration of classification models is a technique to estimate the true posterior probability of the predicted class, which is critical for ensuring reliable decision-making in practical applications. Existin…

Can a Confident Prior Replace a Cold Posterior?

2024-03-02 · Martin Marek, Brooks Paige, Pavel Izmailov

Benchmark datasets used for image classification tend to have very low levels of label noise. When Bayesian neural networks are trained on these datasets, they often underfit, misrepresenting the aleatoric uncertainty of…

image-classificationImage Classification