Self-Supervised Feature Learning by Learning to Spot Artifacts

06/13/2018
by   Simon Jenni, et al.
4

We introduce a novel self-supervised learning method based on adversarial training. Our objective is to train a discriminator network to distinguish real images from images with synthetic artifacts, and then to extract features from its intermediate layers that can be transferred to other data domains and tasks. To generate images with artifacts, we pre-train a high-capacity autoencoder and then we use a damage and repair strategy: First, we freeze the autoencoder and damage the output of the encoder by randomly dropping its entries. Second, we augment the decoder with a repair network, and train it in an adversarial manner against the discriminator. The repair network helps generate more realistic images by inpainting the dropped feature entries. To make the discriminator focus on the artifacts, we also make it predict what entries in the feature were dropped. We demonstrate experimentally that features learned by creating and spotting artifacts achieve state of the art performance in several benchmarks.

READ FULL TEXT

page 1

page 3

page 6

page 8

research
02/06/2018

Learning Image Representations by Completing Damaged Jigsaw Puzzles

In this paper, we explore methods of complicating self-supervised tasks ...
research
05/29/2023

Controllable Path of Destruction

Path of Destruction (PoD) is a self-supervised method for learning itera...
research
03/31/2023

INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields

Perception datasets for agriculture are limited both in quantity and div...
research
05/14/2019

An Improved Self-supervised GAN via Adversarial Training

We propose to improve unconditional Generative Adversarial Networks (GAN...
research
12/22/2016

Learning from Simulated and Unsupervised Images through Adversarial Training

With recent progress in graphics, it has become more tractable to train ...
research
04/23/2023

End-to-End Feasible Optimization Proxies for Large-Scale Economic Dispatch

The paper proposes a novel End-to-End Learning and Repair (E2ELR) archit...

Please sign up or login with your details

Forgot password? Click here to reset