RenderGAN: Generating Realistic Labeled Data

11/04/2016
by   Leon Sixt, et al.
0

Deep Convolutional Neuronal Networks (DCNNs) are showing remarkable performance on many computer vision tasks. Due to their large parameter space, they require many labeled samples when trained in a supervised setting. The costs of annotating data manually can render the use of DCNNs infeasible. We present a novel framework called RenderGAN that can generate large amounts of realistic, labeled images by combining a 3D model and the Generative Adversarial Network framework. In our approach, image augmentations (e.g. lighting, background, and detail) are learned from unlabeled data such that the generated images are strikingly realistic while preserving the labels known from the 3D model. We apply the RenderGAN framework to generate images of barcode-like markers that are attached to honeybees. Training a DCNN on data generated by the RenderGAN yields considerably better performance than training it on various baselines.

READ FULL TEXT

page 2

page 7

page 8

page 12

page 13

page 15

10/02/2016

Deep unsupervised learning through spatial contrasting

Convolutional networks have marked their place over the last few years a...
09/17/2018

Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation

This paper deals with a method for generating realistic labeled masses. ...
08/11/2020

SAFRON: Stitching Across the Frontier for Generating Colorectal Cancer Histology Images

Synthetic images can be used for the development and evaluation of deep ...
03/18/2021

MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels

Supervised learning techniques are at the center of many tasks in remote...
05/19/2017

Sparse Coding on Stereo Video for Object Detection

Deep Convolutional Neural Networks (DCNN) require millions of labeled tr...
11/19/2019

Solar Event Tracking with Deep Regression Networks: A Proof of Concept Evaluation

With the advent of deep learning for computer vision tasks, the need for...
12/08/2020

VAE-Info-cGAN: Generating Synthetic Images by Combining Pixel-level and Feature-level Geospatial Conditional Inputs

Training robust supervised deep learning models for many geospatial appl...