# Pseudo-D: Informing Multi-View Uncertainty Estimation with Calibrated Neural Training Dynamics

arXiv: https://arxiv.org/abs/2509.11800 · HTML: https://mlsanity.com/paper/2509.11800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 16 of 16)

- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibration](https://mlsanity.com/paper/1910.12656/) (2019)
- [Identifying Mislabeled Data using the Area Under the Margin Ranking](https://mlsanity.com/paper/2001.10528/) (2020)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [Self-Adaptive Training: beyond Empirical Risk Minimization](https://mlsanity.com/paper/2002.10319/) (2020)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [Provable Dynamic Fusion for Low-Quality Multimodal Data](https://mlsanity.com/paper/2306.02050/) (2023)
- [Towards Better Selective Classification](https://mlsanity.com/paper/2206.09034/) (2022)
- [Majority Vote of Diverse Classifiers for Late Fusion](https://mlsanity.com/paper/1404.7796/) (2014)
- [Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data](https://mlsanity.com/paper/2210.13043/) (2022)
- [A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms](https://mlsanity.com/paper/2108.00080/) (2021)
- [Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis](https://mlsanity.com/paper/2403.06024/) (2024)
- [Reliable Multi-View Learning with Conformal Prediction for Aortic Stenosis Classification in Echocardiography](https://mlsanity.com/paper/2409.09680/) (2024)

## Abstract (arXiv)

Computer-aided diagnosis systems must make critical decisions from medical images that are often noisy, ambiguous, or conflicting, yet today's models are trained on overly simplistic labels that ignore diagnostic uncertainty. One-hot labels erase inter-rater variability and force models to make overconfident predictions, especially when faced with incomplete or artifact-laden inputs. We address this gap by introducing a novel framework that brings uncertainty back into the label space. Our method leverages neural network training dynamics (NNTD) to assess the inherent difficulty of each training sample. By aggregating and calibrating model predictions during training, we generate uncertainty-aware pseudo-labels that reflect the ambiguity encountered during learning. This label augmentation approach is architecture-agnostic and can be applied to any supervised learning pipeline to enhance uncertainty estimation and robustness. We validate our approach on a challenging echocardiography classification benchmark, demonstrating superior performance over specialized baselines in calibration, selective classification, and multi-view fusion.