# DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation

arXiv: https://arxiv.org/abs/2403.10831 · HTML: https://mlsanity.com/paper/2403.10831/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 16 Mar 2024.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Stochastic Variational Video Prediction](https://mlsanity.com/paper/1710.11252/) (2017)
- [Model-Agnostic Interpretability of Machine Learning](https://mlsanity.com/paper/1606.05386/) (2016)
- [DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation](https://mlsanity.com/paper/1506.06448/) (2015)
- [Resolution Dependent GAN Interpolation for Controllable Image Synthesis Between Domains](https://mlsanity.com/paper/2010.05334/) (2020)
- [Interpolated Convolutional Networks for 3D Point Cloud Understanding](https://mlsanity.com/paper/1908.04512/) (2019)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)
- [Using Captum to Explain Generative Language Models](https://mlsanity.com/paper/2312.05491/) (2023)
- [Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment](https://mlsanity.com/paper/2202.02838/) (2022)
- [RES: A Robust Framework for Guiding Visual Explanation](https://mlsanity.com/paper/2206.13413/) (2022)
- [A unified model for continuous conditional video prediction](https://mlsanity.com/paper/2210.05810/) (2022)
- [Saliency-Regularized Deep Multi-Task Learning](https://mlsanity.com/paper/2207.01117/) (2022)
- [XAI-CLASS: Explanation-Enhanced Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2311.00189/) (2023)

## Built on by (most cited first, 4 of 4)

- [Concerning Uncertainty -- A Systematic Survey of Uncertainty-Aware XAI](https://mlsanity.com/paper/2603.26838/) (2026)
- [LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models](https://mlsanity.com/paper/2406.14862/) (2024)
- [MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis](https://mlsanity.com/paper/2602.17901/) (2026)
- [ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion](https://mlsanity.com/paper/2511.17068/) (2025)

## Abstract (arXiv)

Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications.