# Non-Linear Outlier Synthesis for Out-of-Distribution Detection

arXiv: https://arxiv.org/abs/2411.13619 · HTML: https://mlsanity.com/paper/2411.13619/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2024.

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

- [GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection](https://mlsanity.com/paper/2510.17131/) (2025)
- [Geometrically Constrained Outlier Synthesis](https://mlsanity.com/paper/2603.08413/) (2026)
- [Modality-Aware Out-of-Distribution Detection for Multi-Modal Action Recognition](https://mlsanity.com/paper/2606.24404/) (2026)
- [Beyond Empirical Support: Structured Outlier Generation via Sinkhorn Optimal Transport](https://mlsanity.com/paper/2609.31470/) (2026)

## Abstract (arXiv)

The reliability of supervised classifiers is severely hampered by their limitations in dealing with unexpected inputs, leading to great interest in out-of-distribution (OOD) detection. Recently, OOD detectors trained on synthetic outliers, especially those generated by large diffusion models, have shown promising results in defining robust OOD decision boundaries. Building on this progress, we present NCIS, which enhances the quality of synthetic outliers by operating directly in the diffusion's model embedding space rather than combining disjoint models as in previous work and by modeling class-conditional manifolds with a conditional volume-preserving network for more expressive characterization of the training distribution. We demonstrate that these improvements yield new state-of-the-art OOD detection results on standard ImageNet100 and CIFAR100 benchmarks and provide insights into the importance of data pre-processing and other key design choices. We make our code available at urlhttps://github.com/LarsDoorenbos/NCIS.