# Not All Confusion Is Equal: A Source-Aware Uncertainty Diagnosis for Fine-Grained Aircraft Detection

arXiv: https://arxiv.org/abs/2609.29959 · HTML: https://mlsanity.com/paper/2609.29959/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 24 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 17 of 17)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Laplace Redux -- Effortless Bayesian Deep Learning](https://mlsanity.com/paper/2106.14806/) (2021)
- [Oriented R-CNN for Object Detection](https://mlsanity.com/paper/2108.05699/) (2021)
- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [MMRotate: A Rotated Object Detection Benchmark using PyTorch](https://mlsanity.com/paper/2204.13317/) (2022)
- [Part-based R-CNNs for Fine-grained Category Detection](https://mlsanity.com/paper/1407.3867/) (2014)
- [A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglement](https://mlsanity.com/paper/2204.09308/) (2022)
- [Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data](https://mlsanity.com/paper/2210.13043/) (2022)
- [Not Just How Much, But Where: Decomposing Epistemic Uncertainty into Per-Class Contributions](https://mlsanity.com/paper/2602.21160/) (2026)

## Abstract (arXiv)

Fine-grained object detectors are commonly evaluated with confusion matrices, which show where the model is confused but not why, nor whether the confusion can be reduced. We argue that confusion can be attributed to distinct, separable sources, each quantitatively measurable, turning a passive measurement into actionable guidance. We present A2E2, a diagnostic tool that decomposes the sources of confusion along two axes, aleatoric, epistemic × within-class, between-class, giving a 2×2 taxonomy that enumerates the source types. Each quadrant is measured by its own quantity, computed in one of three places (input geometry, output-space disagreement, and the bias-parameter posterior), so the two epistemic sources are separated by construction rather than by an empirical correlation. On fine-grained aircraft detection, the four quadrants become four named sources with their own remedy verdict: affinity (geometric similarity, irreducible from size alone), heterogeneity (geometrically heterogeneous sub-variants, pointing to re-labeling rather than more data), contested (an insufficiently trained but learnable boundary, improvable), and collapsed (a class starved of data, reducible). After attributing the confusion to a specific reducible source, we apply a targeted intervention and verify experimentally that it reduces the diagnosed source specifically while leaving the irreducible sources unchanged. A2E2 thus turns confusion measurement into a concrete, validatable and actionable "diagnosis" in which the same off-diagonal mass can carry opposite causes and opposite remedies. We also state this framework's limits, including which sources are only partially identifiable on this specific dataset and why.