# DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions

arXiv: https://arxiv.org/abs/2109.13237 · HTML: https://mlsanity.com/paper/2109.13237/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 27 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review](https://mlsanity.com/paper/1611.00740/) (2016)
- [Online Deep Learning: Learning Deep Neural Networks on the Fly](https://mlsanity.com/paper/1711.03705/) (2017)
- [Towards neural networks that provably know when they don't know](https://mlsanity.com/paper/1909.12180/) (2019)
- [Discriminative out-of-distribution detection for semantic segmentation](https://mlsanity.com/paper/1808.07703/) (2018)
- [Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output](https://mlsanity.com/paper/1910.10307/) (2019)
- [Provably Robust Detection of Out-of-distribution Data (almost) for free](https://mlsanity.com/paper/2106.04260/) (2021)
- [Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning](https://mlsanity.com/paper/2103.00869/) (2021)

## Abstract (arXiv)

Deep Learning models possess two key traits that, in combination, make their use in the real world a risky prospect. One, they do not typically generalize well outside of the distribution for which they were trained, and two, they tend to exhibit confident behavior regardless of whether or not they are producing meaningful outputs. While Deep Learning possesses immense power to solve realistic, high-dimensional problems, these traits in concert make it difficult to have confidence in their real-world applications. To overcome this difficulty, the task of Out-Of-Distribution (OOD) Detection has been defined, to determine when a model has received an input from outside of the distribution for which it is trained to operate. This paper introduces and examines a novel methodology, DOODLER, for OOD Detection, which directly leverages the traits which result in its necessity. By training a Variational Auto-Encoder (VAE) on the same data as another Deep Learning model, the VAE learns to accurately reconstruct In-Distribution (ID) inputs, but not to reconstruct OOD inputs, meaning that its failure state can be used to perform OOD Detection. Unlike other work in the area, DOODLER requires only very weak assumptions about the existence of an OOD dataset, allowing for more realistic application. DOODLER also enables pixel-wise segmentations of input images by OOD likelihood, and experimental results show that it matches or outperforms methodologies that operate under the same constraints.