Boundary of Distribution Support Generator (BDSG): Sample Generation on the Boundary

TL;DR

This paper introduces BDSG, a novel invertible-residual-network-based model for generating samples on the boundary of data distributions, improving out-of-distribution detection and boundary approximation in complex, multimodal datasets.

Contribution

It proposes a new boundary generator using IResNet and ResFlow, addressing limitations of GANs in capturing distribution tails and multimodal supports for anomaly detection.

Findings

Effective boundary sample generation on synthetic and real datasets

Competitive out-of-distribution detection performance

Addresses non-convex, multimodal distribution supports

Abstract

Generative models, such as Generative Adversarial Networks (GANs), have been used for unsupervised anomaly detection. While performance keeps improving, several limitations exist particularly attributed to difficulties at capturing multimodal supports and to the ability to approximate the underlying distribution closer to the tails, i.e. the boundary of the distribution's support. This paper proposes an approach that attempts to alleviate such shortcomings. We propose an invertible-residual-network-based model, the Boundary of Distribution Support Generator (BDSG). GANs generally do not guarantee the existence of a probability distribution and here, we use the recently developed Invertible Residual Network (IResNet) and Residual Flow (ResFlow), for density estimation. These models have not yet been used for anomaly detection. We leverage IResNet and ResFlow for Out-of-Distribution (OoD) sample detection and for sample generation on the boundary using a compound loss function that forces the samples to lie on the boundary. The BDSG addresses non-convex support, disjoint components, and multimodal distributions. Results on synthetic data and data from multimodal distributions, such as MNIST and CIFAR-10, demonstrate competitive performance compared to methods from the literature.