# Out-of-Distribution Detection of Melanoma using Normalizing Flows

arXiv: https://arxiv.org/abs/2103.12672 · HTML: https://mlsanity.com/paper/2103.12672/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 45 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 29 of 29)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Likelihood Ratios for Out-of-Distribution Detection](https://mlsanity.com/paper/1906.02845/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [Neural Autoregressive Flows](https://mlsanity.com/paper/1804.00779/) (2018)
- [Stabilizing Training of Generative Adversarial Networks through Regularization](https://mlsanity.com/paper/1705.09367/) (2017)
- [GraphNVP: An Invertible Flow Model for Generating Molecular Graphs](https://mlsanity.com/paper/1905.11600/) (2019)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)
- [Equivariant flow-based sampling for lattice gauge theory](https://mlsanity.com/paper/2003.06413/) (2020)
- [VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation](https://mlsanity.com/paper/1903.01434/) (2019)
- [Latent Normalizing Flows for Discrete Sequences](https://mlsanity.com/paper/1901.10548/) (2019)
- [Targeted free energy estimation via learned mappings](https://mlsanity.com/paper/2002.04913/) (2020)
- [Sum-of-Squares Polynomial Flow](https://mlsanity.com/paper/1905.02325/) (2019)
- [Equivariant Flows: sampling configurations for multi-body systems with symmetric energies](https://mlsanity.com/paper/1910.00753/) (2019)
- [FloWaveNet : A Generative Flow for Raw Audio](https://mlsanity.com/paper/1811.02155/) (2018)
- [Leveraging exploration in off-policy algorithms via normalizing flows](https://mlsanity.com/paper/1905.06893/) (2019)
- [Improving Variational Auto-Encoders using Householder Flow](https://mlsanity.com/paper/1611.09630/) (2016)
- [Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies](https://mlsanity.com/paper/1906.02771/) (2019)
- [Wavelet Flow: Fast Training of High Resolution Normalizing Flows](https://mlsanity.com/paper/2010.13821/) (2020)
- [A RAD approach to deep mixture models](https://mlsanity.com/paper/1903.07714/) (2019)
- [Universal audio synthesizer control with normalizing flows](https://mlsanity.com/paper/1907.00971/) (2019)
- [Randomized Value Functions via Multiplicative Normalizing Flows](https://mlsanity.com/paper/1806.02315/) (2018)

## Abstract (arXiv)

Generative modelling has been a topic at the forefront of machine learning research for a substantial amount of time. With the recent success in the field of machine learning, especially in deep learning, there has been an increased interest in explainable and interpretable machine learning. The ability to model distributions and provide insight in the density estimation and exact data likelihood is an example of such a feature. Normalizing Flows (NFs), a relatively new research field of generative modelling, has received substantial attention since it is able to do exactly this at a relatively low cost whilst enabling competitive generative results. While the generative abilities of NFs are typically explored, we focus on exploring the data distribution modelling for Out-of-Distribution (OOD) detection. Using one of the state-of-the-art NF models, GLOW, we attempt to detect OOD examples in the ISIC dataset. We notice that this model under performs in conform related research. To improve the OOD detection, we explore the masking methods to inhibit co-adaptation of the coupling layers however find no substantial improvement. Furthermore, we utilize Wavelet Flow which uses wavelets that can filter particular frequency components, thus simplifying the modeling process to data-driven conditional wavelet coefficients instead of complete images. This enables us to efficiently model larger resolution images in the hopes that it would capture more relevant features for OOD. The paper that introduced Wavelet Flow mainly focuses on its ability of sampling high resolution images and did not treat OOD detection. We present the results and propose several ideas for improvement such as controlling frequency components, using different wavelets and using other state-of-the-art NF architectures.