Synthesize-It-Classifier: Learning a Generative Classifier through RecurrentSelf-analysis
release_2owummubyrgynfckaqxij3dxqy
by
Arghya Pal, Rapha Phan, KokSheik Wong
2021
Abstract
In this work, we show the generative capability of an image classifier
network by synthesizing high-resolution, photo-realistic, and diverse images at
scale. The overall methodology, called Synthesize-It-Classifier (STIC), does
not require an explicit generator network to estimate the density of the data
distribution and sample images from that, but instead uses the classifier's
knowledge of the boundary to perform gradient ascent w.r.t. class logits and
then synthesizes images using Gram Matrix Metropolis Adjusted Langevin
Algorithm (GRMALA) by drawing on a blank canvas. During training, the
classifier iteratively uses these synthesized images as fake samples and
re-estimates the class boundary in a recurrent fashion to improve both the
classification accuracy and quality of synthetic images. The STIC shows the
mixing of the hard fake samples (i.e. those synthesized by the one hot class
conditioning), and the soft fake samples (which are synthesized as a convex
combination of classes, i.e. a mixup of classes) improves class interpolation.
We demonstrate an Attentive-STIC network that shows an iterative drawing of
synthesized images on the ImageNet dataset that has thousands of classes. In
addition, we introduce the synthesis using a class conditional score classifier
(Score-STIC) instead of a normal image classifier and show improved results on
several real-world datasets, i.e. ImageNet, LSUN, and CIFAR 10.
In text/plain
format
Archived Files and Locations
application/pdf 15.7 MB
file_l2st3blmxvabzjrbgndw4qhhre
|
arxiv.org (repository) web.archive.org (webarchive) |
2103.14212v1
access all versions, variants, and formats of this works (eg, pre-prints)