Localising In Complex Scenes Using Balanced Adversarial Adaptation

by   Gil Avraham, et al.

Domain adaptation and generative modelling have collectively mitigated the expensive nature of data collection and labelling by leveraging the rich abundance of accurate, labelled data in simulation environments. In this work, we study the performance gap that exists between representations optimised for localisation on simulation environments and the application of such representations in a real-world setting. Our method exploits the shared geometric similarities between simulation and real-world environments whilst maintaining invariance towards visual discrepancies. This is achieved by optimising a representation extractor to project both simulated and real representations into a shared representation space. Our method uses a symmetrical adversarial approach which encourages the representation extractor to conceal the domain that features are extracted from and simultaneously preserves robust attributes between source and target domains that are beneficial for localisation. We evaluate our method by adapting representations optimised for indoor Habitat simulated environments (Matterport3D and Replica) to a real-world indoor environment (Active Vision Dataset), showing that it compares favourably against fully-supervised approaches.


page 1

page 2

page 3

page 4


Domain Adaptation Through Task Distillation

Deep networks devour millions of precisely annotated images to build the...

Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation

Domain adaptation is a common problem in robotics, with applications suc...

SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis

To represent the biological variability of clinical neuroimaging populat...

DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Indoor Semantic Segmentation

Deep learning approaches achieve prominent success in 3D semantic segmen...

Domain Separation Networks

The cost of large scale data collection and annotation often makes the a...

Learning Transferable UAV for Forest Visual Perception

In this paper, we propose a new pipeline of training a monocular UAV to ...

Please sign up or login with your details

Forgot password? Click here to reset