Image Decomposition and Classification Through a Generative Model

Houpu Yao, Malcolm Regan, Yezhou Yang, Yi Ren

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

Abstract

We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational autoencoder that learns both the decomposition of inputs and the distributions of the resulting components. During test, we jointly optimize the latent variables of the generator and the relaxed component labels to find the best match between the given input and the output of the generator. The model demonstrates promising performance at recognizing overlapping components from the multiMNIST dataset, and novel component combinations from a traffic sign dataset. Experiments also show that the proposed model achieves high robustness on MNIST and NORB datasets, in particular for high-strength gradient attacks and non-gradient attacks.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Image Processing, ICIP 2019 - Proceedings
PublisherIEEE Computer Society
Pages400-404
Number of pages5
ISBN (Electronic)9781538662496
DOIs
StatePublished - Sep 2019
Event26th IEEE International Conference on Image Processing, ICIP 2019 - Taipei, Taiwan, Province of China
Duration: Sep 22 2019Sep 25 2019

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2019-September
ISSN (Print)1522-4880

Conference

Conference26th IEEE International Conference on Image Processing, ICIP 2019
CountryTaiwan, Province of China
CityTaipei
Period9/22/199/25/19

Keywords

  • Generative model
  • adversarial defense
  • classification

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'Image Decomposition and Classification Through a Generative Model'. Together they form a unique fingerprint.

Cite this