papers AI Learner
The Github is limit! Click to go to the new site.

SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation

2019-05-18
Daniel Gordon, Abhishek Kadian, Devi Parikh, Judy Hoffman, Dhruv Batra

Abstract

We propose SplitNet, a method for decoupling visual perception and policy learning. By incorporating auxiliary tasks and selective learning of portions of the model, we explicitly decompose the learning objectives for visual navigation into perceiving the world and acting on that perception. We show dramatic improvements over baseline models on transferring between simulators, an encouraging step towards Sim2Real. Additionally, SplitNet generalizes better to unseen environments from the same simulator and transfers faster and more effectively to novel embodied navigation tasks. Further, given only a small sample from a target domain, SplitNet can match the performance of traditional end-to-end pipelines which receive the entire dataset. Code and video are available at https://github.com/facebookresearch/splitnet and https://youtu.be/TJkZcsD2vrc

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.07512

PDF

http://arxiv.org/pdf/1905.07512


Similar Posts

Comments