Boundary Of Distribution Support Generator (BDSG): Sample Generation On The Boundary

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publication2020 IEEE International Conference on Image Processing (ICIP)
PublisherIEEE
Pages803-807
Number of pages5
ISBN (Electronic)978-1-7281-6395-6
ISBN (Print)978-1-7281-6396-3
DOIs
Publication statusPublished - 30 Sep 2020
Event2020 IEEE International Conference on Image Processing (ICIP) - Abu Dhabi, United Arab Emirates
Duration: 25 Oct 202028 Oct 2020

Conference

Conference2020 IEEE International Conference on Image Processing (ICIP)
Period25/10/2028/10/20

Keywords

  • Anomaly detection
  • Generators
  • Gallium nitride
  • Data models
  • Convergence
  • Estimation
  • Computational modeling

Fingerprint

Dive into the research topics of 'Boundary Of Distribution Support Generator (BDSG): Sample Generation On The Boundary'. Together they form a unique fingerprint.

Cite this