# TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection

arXiv: https://arxiv.org/abs/2512.00229 · HTML: https://mlsanity.com/paper/2512.00229/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 27 of 27)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [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)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Evidential Deep Learning to Quantify Classification Uncertainty](https://mlsanity.com/paper/1806.01768/) (2018)
- [Understanding Deep Image Representations by Inverting Them](https://mlsanity.com/paper/1412.0035/) (2014)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Synthesizing the preferred inputs for neurons in neural networks via deep generator networks](https://mlsanity.com/paper/1605.09304/) (2016)
- [Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts](https://mlsanity.com/paper/2006.09239/) (2020)
- [DEUP: Direct Epistemic Uncertainty Prediction](https://mlsanity.com/paper/2102.08501/) (2021)
- [Exploring the Landscape of Spatial Robustness](https://mlsanity.com/paper/1712.02779/) (2017)
- [Post-hoc Uncertainty Learning using a Dirichlet Meta-Model](https://mlsanity.com/paper/2212.07359/) (2022)
- [Uncertainty-Aware Optimal Transport for Semantically Coherent Out-of-Distribution Detection](https://mlsanity.com/paper/2303.10449/) (2023)
- [Autoinverse: Uncertainty Aware Inversion of Neural Networks](https://mlsanity.com/paper/2208.13780/) (2022)
- [Landscape Learning for Neural Network Inversion](https://mlsanity.com/paper/2206.09027/) (2022)
- [Network Inversion of Binarised Neural Nets](https://mlsanity.com/paper/2402.11995/) (2024)
- [Network Inversion of Convolutional Neural Nets](https://mlsanity.com/paper/2407.18002/) (2024)
- [Uncertainty-Aware Out-of-Distribution Detection with Gaussian Processes](https://mlsanity.com/paper/2412.20918/) (2024)
- [Network Inversion for Generating Confidently Classified Counterfeits](https://mlsanity.com/paper/2503.20187/) (2025)
- [Network Inversion for Uncertainty-Aware Out-of-Distribution Detection](https://mlsanity.com/paper/2505.23448/) (2025)

## Abstract (arXiv)

Deep neural networks often struggle to recognize when an input lies outside their training experience, leading to unreliable and overconfident predictions. Building dependable machine learning systems therefore requires methods that can both estimate predictive textituncertainty and detect textitout-of-distribution (OOD) samples in a unified manner. In this paper, we propose TIE: a Training--Inversion--Exclusion framework for visually interpretable and uncertainty-guided anomaly detection that jointly addresses these challenges through iterative refinement. TIE extends a standard n-class classifier to an (n+1)-class model by introducing a garbage class initialized with Gaussian noise to represent outlier inputs. Within each epoch, TIE performs a closed-loop process of textittraining, inversion, and exclusion, where highly uncertain inverted samples reconstructed from the just-trained classifier are excluded into the garbage class. Over successive iterations, the inverted samples transition from noisy artifacts into visually coherent class prototypes, providing transparent insight into how the model organizes its learned manifolds. During inference, TIE rejects OOD inputs by either directly mapping them to the garbage class or producing low-confidence, uncertain misclassifications within the in-distribution classes that are easily separable, all without relying on external OOD datasets. A comprehensive threshold-based evaluation using multiple OOD metrics and performance measures such as textitAUROC, textitAUPR, and textitFPR@95%TPR demonstrates that TIE offers a unified and interpretable framework for robust anomaly detection and calibrated uncertainty estimation (UE) achieving near-perfect OOD detection with (!≈!) 0 FPR@95%TPR when trained on MNIST or FashionMNIST and tested against diverse unseen datasets.