Object Discovery with a Copy-Pasting GAN

05/27/2019
by   Relja Arandjelović, et al.
12

We tackle the problem of object discovery, where objects are segmented for a given input image, and the system is trained without using any direct supervision whatsoever. A novel copy-pasting GAN framework is proposed, where the generator learns to discover an object in one image by compositing it into another image such that the discriminator cannot tell that the resulting image is fake. After carefully addressing subtle issues, such as preventing the generator from `cheating', this game results in the generator learning to select objects, as copy-pasting objects is most likely to fool the discriminator. The system is shown to work well on four very different datasets, including large object appearance variations in challenging cluttered backgrounds.

READ FULL TEXT

page 3

page 4

page 7

page 8

page 14

research
02/21/2018

A Study into the similarity in generator and discriminator in GAN architecture

One popular generative model that has high-quality results is the Genera...
research
06/05/2018

Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

While great progress has been made recently in automatic image manipulat...
research
06/16/2017

Perceptual Generative Adversarial Networks for Small Object Detection

Detecting small objects is notoriously challenging due to their low reso...
research
04/04/2019

UU-Nets Connecting Discriminator and Generator for Image to Image Translation

Adversarial generative model have successfully manifest itself in image ...
research
05/27/2019

Unsupervised Object Segmentation by Redrawing

Object segmentation is a crucial problem that is usually solved by using...
research
03/31/2017

Unsupervised Holistic Image Generation from Key Local Patches

We introduce a new problem of generating an image based on a small numbe...
research
03/06/2022

A Robust Framework of Chromosome Straightening with ViT-Patch GAN

Chromosomes exhibit non-rigid and non-articulated nature with varying de...

Please sign up or login with your details

Forgot password? Click here to reset