Network Inversion for Uncertainty-Aware Out-of-Distribution Detection (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41393-41395
DOI: 10.1609/aaai.v40i48.42282 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Pirzada Suhail und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Out-of-distribution (OOD) detection and uncertainty estimation (UE) are critical components for building safe machine learning systems. In this work, we propose a novel framework that combines network inversion with classifier training to simultaneously address both OOD detection and uncertainty estimation. We extend a standard n-class classifier by adding an (n+1)-th "garbage" class to capture outliers, initially populated with random Gaussian noise. After each training epoch, we use network inversion to reconstruct inputs for all classes; incoherent reconstructions are assigned to the garbage class for retraining. This iterative cycle of training, inversion, and exclusion continues until inverted samples resemble in-distribution data and uncertainty drops, indicating learned decision boundaries and cleaner class manifolds. At inference, the model detects OOD inputs by classifying them as garbage, with confidence scores estimating uncertainty. Unlike prior methods, this approach requires no external OOD data or post-hoc calibration, providing a simple, unified solution for robust classification, OOD detection, and uncertainty estimation.
Zitieren
APA
Suhail, P., Shaik, R. A., Bala, G., & Sethi, A. (2026). Network Inversion for Uncertainty-Aware Out-of-Distribution Detection (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41393-41395. https://doi.org/10.1609/aaai.v40i48.42282
Vancouver
Suhail P, Shaik RA, Bala G, Sethi A. Network Inversion for Uncertainty-Aware Out-of-Distribution Detection (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41393-41395. doi:10.1609/aaai.v40i48.42282
BibTeX
@article{Suhail2026,
author = {Suhail, Pirzada and Shaik, Rehna Afroz and Bala, Gouranga and Sethi, Amit},
title = {Network Inversion for Uncertainty-Aware Out-of-Distribution Detection (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41393--41395},
doi = {10.1609/aaai.v40i48.42282}
}
EUVIMED