{"ID":2874368,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.05485","arxiv_id":"2509.05485","title":"Prior Distribution and Model Confidence","abstract":"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.","short_abstract":"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 re...","url_abs":"https://arxiv.org/abs/2509.05485","url_pdf":"https://arxiv.org/pdf/2509.05485v2","authors":"[\"Maksim Kazanskii\",\"Artem Kasianov\"]","published":"2025-09-05T20:17:26Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}