# Image Decomposition and Classification through a Generative Model

arXiv: https://arxiv.org/abs/1902.03361 · HTML: https://mlsanity.com/paper/1902.03361/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2019.

## Built on by (most cited first, 1 of 1)

- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)

## Abstract (arXiv)

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.