A general approach to bridge the reality-gap

09/03/2020
by   Michael Lomnitz, et al.
0

Employing machine learning models in the real world requires collecting large amounts of data, which is both time consuming and costly to collect. A common approach to circumvent this is to leverage existing, similar data-sets with large amounts of labelled data. However, models trained on these canonical distributions do not readily transfer to real-world ones. Domain adaptation and transfer learning are often used to breach this "reality gap", though both require a substantial amount of real-world data. In this paper we discuss a more general approach: we propose learning a general transformation to bring arbitrary images towards a canonical distribution where we can naively apply the trained machine learning models. This transformation is trained in an unsupervised regime, leveraging data augmentation to generate off-canonical examples of images and training a Deep Learning model to recover their original counterpart. We quantify the performance of this transformation using pre-trained ImageNet classifiers, demonstrating that this procedure can recover half of the loss in performance on the distorted data-set. We then validate the effectiveness of this approach on a series of pre-trained ImageNet models on a real world data set collected by printing and photographing images in different lighting conditions.

READ FULL TEXT

Authors

page 6

page 7

12/18/2018

Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks

Real world data, especially in the domain of robotics, is notoriously co...
01/17/2019

Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails

Robots hold promise in many scenarios involving outdoor use, such as sea...
09/29/2021

Towards a theory of out-of-distribution learning

What is learning? 20^st century formalizations of learning theory – whic...
06/17/2022

Representational Multiplicity Should Be Exposed, Not Eliminated

It is prevalent and well-observed, but poorly understood, that two machi...
11/24/2020

Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agents

Deep reinforcement learning models are notoriously data hungry, yet real...
12/24/2020

Seed Phenotyping on Neural Networks using Domain Randomization and Transfer Learning

Seed phenotyping is the idea of analyzing the morphometric characteristi...
10/14/2021

A Comprehensive Study on Torchvision Pre-trained Models for Fine-grained Inter-species Classification

This study aims to explore different pre-trained models offered in the T...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.