Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
Learning is an inherently continuous phenomenon. When humans learn a new task there is no explicit distinction between training and inference. As we learn a task, we keep learning about it while performing the task. What we learn and how we learn it varies during different stages of learning. Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings. This is in contrast with conventional settings in machine learning where a trained model is frozen during inference. In this paper we study the problem of learning to learn at both training and test time in the context of visual navigation. A fundamental challenge in navigation is generalization to unseen scenes. In this paper we propose a self-adaptive visual navigation method (SAVN) which learns to adapt to new environments without any explicit supervision. Our solution is a meta-reinforcement learning approach where an agent learns a self-supervised interaction loss that encourages effective navigation. Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes. Our code and data are available at: https://github.com/allenai/savn.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 5×
“By using our training objective with the added hand-crafted prediction loss (referred to as ‘Ours - prediction’), we outperform the baseline non-adaptive model with prediction (referred to as ‘A3C w/ prediction’) by 3.3% for all trajectories and 4.8% for trajectories of at least length 5 in terms of success rate.”
InfluentialContext Encoders: Feature Learning by Inpainting
Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., & Efros, A. A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.278 · Cited by 5,691
Unsupervised Visual Representation Learning by Context Prediction
Doersch, C., Gupta, A., & Efros, A. A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.167 · Cited by 2,629 · cited 1×
“Different types of self-supervision have been explored in the literature [1, 19, 11, 42, 49, 36, 34, 32].”
BackgroundCuriosity-Driven Exploration by Self-Supervised Prediction
Pathak, D., Agrawal, P., Efros, A. A., & Darrell, T. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.70 · Cited by 1,815 · cited 1×
“Some works aim to maximize the prediction error in the representation of future states [33, 39].”
BackgroundTarget-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533 · cited 3×
“, [50, 15, 27]) have become popular as they implicitly perform localization, mapping, exploration and semantic recognition end-to-end.”
BackgroundMethodInfluentialSelf-citationAnderson, P., Wu, Q., Teney, D., Bruce, J., Johnson, M., Sunderhauf, N., Reid, I., Gould, S., & van den Hengel, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00387 · Cited by 1,187
Unsupervised Learning of Visual Representations Using Videos
Wang, X., & Gupta, A. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.320 · Cited by 1,005
On evaluation of embodied navigation agents
Anderson, P., Chang, A., Chaplot, D. S., Dosovitskiy, A., Gupta, S., Koltun, V., Kosecka, J., Malik, J., Mottaghi, R., Savva, M., et al. (2018) · arXiv · doi:10.48550/arxiv.1807.06757 · Cited by 622
Self-citationAI2-THOR: An Interactive 3D Environment for Visual AI
Kolve, E., Mottaghi, R., Han, W., VanderBilt, E., Weihs, L., Herrasti, A., Deitke, M., Ehsani, K., Gordon, D., Zhu, Y., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.05474 · Cited by 578 · cited 3×
“We perform our experiments using the AI2-THOR [23] framework.”
MethodInfluentialSelf-citationLearning to Learn: Introduction and Overview
Thrun, S., & Pratt, L. (1998) · Learning to Learn · doi:10.1007/978-1-4615-5529-2_1 · Cited by 521
Error modeling in stereo navigation
Matthies, L., & Shafer, S. (1987) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1987.1087097 · Cited by 509 · cited 1×
“Traditional navigation methods typically perform planning on a given map of the environment or build a map as the exploration proceeds [26, 40, 21, 24, 9, 4].”
BackgroundRL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
Duan, Y., Schulman, J., Chen, X., Bartlett, P. L., Sutskever, I., & Abbeel, P. (2016) · arXiv · doi:10.48550/arxiv.1611.02779 · Cited by 503
Gated-Attention Architectures for Task-Oriented Language Grounding
Chaplot, D. S., Sathyendra, K. M., Pasumarthi, R. K., Rajagopal, D., & Salakhutdinov, R. (2017) · arXiv · doi:10.48550/arxiv.1706.07230 · Cited by 82 · cited 1×
“f other applications such as autonomous driving (e.g., [7]), mapbased city navigation (e.g., [5]) and game play (e.g., [43]). Navigation using language instructions has been explored by various works [3,6,17,47,29]. Our goal is different since we focus on using meta-learning to more effectively navigate new scenes usi…”
Background
Cited by
AI2-THOR: An Interactive 3D Environment for Visual AI
Kolve, E., Mottaghi, R., Han, W., VanderBilt, E., Weihs, L., Herrasti, A., Deitke, M., Ehsani, K., Gordon, D., Zhu, Y., et al. (2017) · arXiv · doi:10.48550/arxiv.1712.05474 · Cited by 578
“t: http://ai2thor. allenai.org/documentation 7. Example Usage of AI2-THOR AI2-THOR has been successfully tested for different applications. We used AI2-THOR for the problem of targetdriven navigation [26,24,22] using deep reinforcement learning and showed that the trained model can be transferred to real robots with s…”
MethodSelf-citationA Survey of Embodied AI: From Simulators to Research Tasks
Duan, J., Yu, S., Tan, H. L., Zhu, H., & Tan, C. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3141105 · Cited by 420
Object Goal Navigation using Goal-Oriented Semantic Exploration
Chaplot, D. S., Gandhi, D., Gupta, A., & Salakhutdinov, R. (2020) · arXiv · doi:10.48550/arxiv.2007.00643 · Cited by 321
“[43] propose a meta-reinforcement learning approach where an agent learns a self-supervised interaction loss that encourages effective navigation to even keep learning in a test environment.”
BackgroundFeng, Y., Chen, J., Xie, J., Zhang, T., Lv, H., & Pan, T. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107646 · Cited by 262
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
Deitke, M., Han, W., Herrasti, A., Kembhavi, A., Kolve, E., Mottaghi, R., Salvador, J., Schwenk, D., VanderBilt, E., Wallingford, M., et al. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00323 · Cited by 220
“[69] use meta-learning to learn a self-supervised navigation policy toward a specified object category.”
BackgroundMethodResultInfluentialSelf-citation
Metadata
- Authors
- Wortsman, M., Ehsani, K., Rastegari, M., Farhadi, A., & Mottaghi, R.
- Venue
- 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2019-06
- Pages
- 6743-6752
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2902577693
- Cited by
- 242
- References
- 16
- FWCI
- 12.42
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.