Transfer Learning From Synthetic To Real Images Using Variational Autoencoders For Precise Position Detection

07/04/2018
by   Tadanobu Inoue, et al.
0

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not achieve the desired performance in the real world due to a gap between synthetic and real images. We propose a method that transfers learned detection of an object position from a simulation environment to the real world. This method uses only a significantly limited dataset of real images while leveraging a large dataset of synthetic images using variational autoencoders. Additionally, the proposed method consistently performed well in different lighting conditions, in the presence of other distractor objects, and on different backgrounds. Experimental results showed that it achieved accuracy of 1.5mm to 3.5mm on average. Furthermore, we showed how the method can be used in a real-world scenario like a "pick-and-place" robotic task.

READ FULL TEXT

page 3

page 4

research
09/20/2017

Transfer learning from synthetic to real images using variational autoencoders for robotic applications

Robotic learning in simulation environments provides a faster, more scal...
research
07/10/2017

Automatic Construction of Real-World Datasets for 3D Object Localization using Two Cameras

Unlike classification, position labels cannot be assigned manually by hu...
research
08/30/2021

Enlisting 3D Crop Models and GANs for More Data Efficient and Generalizable Fruit Detection

Training real-world neural network models to achieve high performance an...
research
05/18/2018

Synthetically Trained Neural Networks for Learning Human-Readable Plans from Real-World Demonstrations

We present a system to infer and execute a human-readable program from a...
research
12/18/2014

Decomposition-Based Domain Adaptation for Real-World Font Recognition

We present a domain adaption framework to address a domain mismatch betw...
research
04/14/2022

Egocentric Human-Object Interaction Detection Exploiting Synthetic Data

We consider the problem of detecting Egocentric HumanObject Interactions...
research
03/31/2015

Real-World Font Recognition Using Deep Network and Domain Adaptation

We address a challenging fine-grain classification problem: recognizing ...

Please sign up or login with your details

Forgot password? Click here to reset