Out-of-Distribution Detection of Melanoma using Normalizing Flows

TL;DR

This paper investigates using Normalizing Flows, specifically GLOW and Wavelet Flow, for detecting out-of-distribution melanoma images, exploring methods to improve detection accuracy and model larger images efficiently.

Contribution

It applies and evaluates Normalizing Flows for OOD detection in melanoma, introduces Wavelet Flow for better high-resolution modeling, and discusses potential improvements.

Findings

Wavelet Flow shows promise in modeling high-resolution images for OOD detection.

Masking methods did not significantly improve OOD detection performance.

Proposed ideas include frequency control and alternative NF architectures.

Abstract

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.