DeepAI AI Chat
Log In Sign Up

DIRL: Domain-Invariant Representation Learning for Sim-to-Real Transfer

11/15/2020
by   Ajay Kumar Tanwani, et al.
berkeley college
1

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In this paper, we present a domain-invariant representation learning (DIRL) algorithm to adapt deep models to the physical environment with a small amount of real data. Existing approaches that only mitigate the covariate shift by aligning the marginal distributions across the domains and assume the conditional distributions to be domain-invariant can lead to ambiguous transfer in real scenarios. We propose to jointly align the marginal (input domains) and the conditional (output labels) distributions to mitigate the covariate and the conditional shift across the domains with adversarial learning, and combine it with a triplet distribution loss to make the conditional distributions disjoint in the shared feature space. Experiments on digit domains yield state-of-the-art performance on challenging benchmarks, while sim-to-real transfer of object recognition for vision-based decluttering with a mobile robot improves from 26.8 a wide variety of objects. Code and supplementary details are available at https://sites.google.com/view/dirl

READ FULL TEXT

page 13

page 14

10/23/2019

Generalized Domain Adaptation with Covariate and Label Shift CO-ALignment

Unsupervised knowledge transfer has a great potential to improve the gen...
02/12/2022

Domain-Invariant Proposals based on a Balanced Domain Classifier for Object Detection

Object recognition from images means to automatically find object(s) of ...
09/18/2019

Transfer Learning with Dynamic Adversarial Adaptation Network

The recent advances in deep transfer learning reveal that adversarial le...
10/04/2021

Learning Domain-Invariant Relationship with Instrumental Variable for Domain Generalization

Domain generalization (DG) aims to learn from multiple source domains a ...
07/31/2021

Conditional Bures Metric for Domain Adaptation

As a vital problem in classification-oriented transfer, unsupervised dom...
02/26/2022

Generalized Label Shift Correction via Minimum Uncertainty Principle: Theory and Algorithm

As a fundamental problem in machine learning, dataset shift induces a pa...
09/12/2020

Revisiting the Threat Space for Vision-based Keystroke Inference Attacks

A vision-based keystroke inference attack is a side-channel attack in wh...