mlsanityData to 7 Oct 2026

SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation

arXiv 1905.07512 ↗First posted 18 May 2019cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

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 is available https://github.com/facebookresearch/splitnet

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2020: 1; 2021: 9; 2022: 10; 2023: 5; 2024: 2; 2025: 2.

29 papers.

Sort:

By area:

  1. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  2. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  3. 2022HUMANISE: Language-conditioned Human Motion Generation in 3D Scenescited by 156
  4. 2022Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environmentscited by 80
  5. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  6. 2021GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Drivingcited by 59
  7. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52
  8. 2023Learning Navigational Visual Representations with Semantic Map Supervisioncited by 40
  9. 2022Towards Versatile Embodied Navigationcited by 26
  10. 2023Selective Visual Representations Improve Convergence and Generalization for Embodied AIcited by 19
  11. 2023Omnidirectional Information Gathering for Knowledge Transfer-based Audio-Visual Navigationcited by 18
  12. 2023XVO: Generalized Visual Odometry via Cross-Modal Self-Trainingcited by 17
17 more
  1. 2020Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learningcited by 14
  2. 2021Environment Predictive Coding for Embodied Agentscited by 12
  3. 2025From Seeing to Experiencing: Scaling Navigation Foundation Models with Reinforcement Learningcited by 11
  4. 2022Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigationcited by 9
  5. 2022Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Visioncited by 4
  6. 2021Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistencycited by 3
  7. 2022A General Purpose Supervisory Signal for Embodied Agentscited by 3
  8. 2024Language-Based Augmentation to Address Shortcut Learning in Object Goal Navigationcited by 3
  9. 2021Deep Learning for Embodied Vision Navigation: A Surveycited by 2
  10. 2023Interactive Semantic Map Representation for Skill-based Visual Object Navigationcited by 2
  11. 2025Generalization in Reinforcement Learning for Radio Access Networkscited by 2
  12. 2021An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigationcited by 1
  13. 2022ASC me to Do Anything: Multi-task Training for Embodied AIcited by 1
  14. 2021VSGM -- Enhance robot task understanding ability through visual semantic graphcited by 0
  15. 2021Egocentric Activity Recognition and Localization on a 3D Mapcited by 0
  16. 2022Towards self-attention based visual navigation in the real worldcited by 0
  17. 2024Model Adaptation for Time Constrained Embodied Controlcited by 0