Filters








127,400 Hits in 4.3 sec

Adaptation and Learning for Image Based Navigation

Supreeth Achar, C.V. Jawahar
<span title="">2008</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ozezavvqujap3ipcejenuvqkmm" style="color: black;">2008 Sixth Indian Conference on Computer Vision, Graphics &amp; Image Processing</a> </i> &nbsp;
In this paper, we present an efficient, adaptive method for qualitative localization using content based image retrieval techniques.  ...  Image based methods are a new approach for solving problems in mobile robotics. Instead of building a metric (3D) model of the environment, these methods work directly in the sensor (image) space.  ...  The focus of this paper is on how learning can improve the performance of an image based robot navigation system.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icvgip.2008.72">doi:10.1109/icvgip.2008.72</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icvgip/AcharJ08.html">dblp:conf/icvgip/AcharJ08</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bpbh6536dfbjhlb4asogkiwztu">fatcat:bpbh6536dfbjhlb4asogkiwztu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808205139/http://web2py.iiit.ac.in/publications/default/download/inproceedings.pdf.c73b0e38-0811-4a38-aada-d73dea09150b.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d4/01/d4014c2e5b96b99974cbb0c5d0daa8bea607613f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icvgip.2008.72"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Unsupervised Domain Adaptation for Visual Navigation [article]

Shangda Li, Devendra Singh Chaplot, Yao-Hung Hubert Tsai, Yue Wu, Louis-Philippe Morency, Ruslan Salakhutdinov
<span title="2020-11-12">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, most learning-based navigation policies are trained and tested in simulation environments.  ...  Advances in visual navigation methods have led to intelligent embodied navigation agents capable of learning meaningful representations from raw RGB images and perform a wide variety of tasks involving  ...  The proposed policy-based image translation for unsupervised visual navigation adaptation. Figure 2 : 2 Policy Decomposition. Figure 3 : 3 Policy-based Consistency Loss.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.14543v2">arXiv:2010.14543v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/evtvmq4wg5gyzoldvwwaupjxde">fatcat:evtvmq4wg5gyzoldvwwaupjxde</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201114114624/https://arxiv.org/pdf/2010.14543v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/71/ba/71bac89b006012922d8b8e53baeb5b3554d3aeab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.14543v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Model-agnostic Metalearning Based Text-driven Visual Navigation Model for Unfamiliar Tasks

Tianfang Xue, Haibin Yu
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
In our work, we put forward a navigation-specific self-adaptive learning mechanism derivated out of MAML learning. 2) Adaptive Learning Approach for visual navigation In this paper we propose a self-adaptive  ...  Yuyang Liu [26] proposes a Memory-based Parameterized Skills Learning (MPSL) model for mapless visual navigation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3023014">doi:10.1109/access.2020.3023014</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fpvxwp3jpbgq7fnpem3m6brld4">fatcat:fpvxwp3jpbgq7fnpem3m6brld4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108141641/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09189802.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bf/6e/bf6e21ea3a029fd6aa9e6e57ee1fcb388cf10ed4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3023014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Applying Content Adaptation to Mobile Learning

Stephen J. H. Yang, Irene Y. L. Chen, Rick Chen
<span title="">2007</span> <i title="IEEE"> Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007) </i> &nbsp;
Based on the results of survey and interview, that is necessary and tremendous impact to m-learning for touch screen to create a suitable content adaptation.  ...  Content adaptation refers to different kinds of software and coding applications that use for learning.  ...  Based the research, author discovered that navigation design ideas were personality and ease navigation for touch screen.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icicic.2007.181">doi:10.1109/icicic.2007.181</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w3ktsiiz65d4fpwqpaj24ezp6e">fatcat:w3ktsiiz65d4fpwqpaj24ezp6e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20130811005135/http://www.ipedr.com/vol13/15-T00026.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/39/ed/39ed7faf30fc724bf027aaab64659e950bc3922e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icicic.2007.181"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning [article]

Qian Luo, Maks Sorokin, Sehoon Ha
<span title="2021-06-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experiments show that our algorithm adapts the learned navigation policy with only three shots for unseen situations with different sensor configurations or different target colors.  ...  We design a policy architecture with latent features between perception and inference networks and quickly adapt the perception network via meta-learning while freezing the inference network.  ...  We tackle this problem based on two steps: the baseline agent learning step and the adaptation step.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.03609v3">arXiv:2011.03609v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/izvn4hq2enfwbes2kufh3zpp3a">fatcat:izvn4hq2enfwbes2kufh3zpp3a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201218034742/https://arxiv.org/pdf/2011.03609v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9a/c6/9ac6272239ce14d40cf17a8ad61485dfa5977a5d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.03609v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

SwiftLink: Serendipitous Navigation Strategy for Large-Scale Document Collections

Marc von Wyl, Stephane Marchand-Maillet
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/mfwemajbqjcy7hji6w3ztzfccu" style="color: black;">2012 23rd International Workshop on Database and Expert Systems Applications</a> </i> &nbsp;
The multiplication of large-scale document collections has created the need for robust and adaptive access strategies in many applicative areas.  ...  However, it exploits user feedback in a navigational procedure to perform an approximation of interactive metric learning procedures.  ...  Essentially, we are based on the setup of metric learning [14] to adapt a measure over the collection and to be able to extract a collection sample suited for further navigation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/dexa.2012.52">doi:10.1109/dexa.2012.52</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/dexaw/WylM12.html">dblp:conf/dexaw/WylM12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qt4upuuxjfaytcnjfeyzshcbie">fatcat:qt4upuuxjfaytcnjfeyzshcbie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150907001538/http://viper.unige.ch/documents/pdf/vonwyl2012-rsmeetdb.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d4/0a/d40ab487641992be14a11585705dcf69022c8cc8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/dexa.2012.52"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

On Embodied Visual Navigation in Real Environments Through Habitat [article]

Marco Rosano, Antonino Furnari, Luigi Gulino, Giovanni Maria Farinella
<span title="2020-10-26">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Visual navigation models based on deep learning can learn effective policies when trained on large amounts of visual observations through reinforcement learning.  ...  In this paper, we propose a tool based on the Habitat simulator which exploits real world images of the environment, together with sensor and actuator noise models, to produce more realistic navigation  ...  noise, actuator noise and appearance gap on a navigation policy learned with virtual observations when tested on real-world visual inputs; 3) adapt a navigation model learned with virtual observations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.13439v1">arXiv:2010.13439v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jbxdrogrureh5jquhqjjlahpsu">fatcat:jbxdrogrureh5jquhqjjlahpsu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029064822/https://arxiv.org/pdf/2010.13439v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2b/3f/2b3fe5993973ac5061e4703c21aa43c5912cb117.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.13439v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
<span title="2020-07-10">2020</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5cekcl3stvfxxfsctgk6zwoqwe" style="color: black;">Patterns</a> </i> &nbsp;
Finally, we discuss several challenges and future topics for the use of adversarial learning, RL, and meta-learning in autonomous systems.  ...  Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability.  ...  ACKNOWLEDGMENTS The authors would like to thank the Editor-in-Chief, Scientific Editor, and anonymous referees for their helpful comments and suggestions, which have greatly improved this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patter.2020.100050">doi:10.1016/j.patter.2020.100050</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33205114">pmid:33205114</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7660378/">pmcid:PMC7660378</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vs7wm2yrwjamjbaml36663wvze">fatcat:vs7wm2yrwjamjbaml36663wvze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210526081609/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC7660378&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/16/7a/167ae5c124eb94d9c2adac999a2a0667d956cc56.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.patter.2020.100050"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7660378" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Cross-View Policy Learning for Street Navigation [article]

Ang Li, Huiyi Hu, Piotr Mirowski, Mehrdad Farajtabar
<span title="2019-09-22">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
called StreetLearn and used for research on navigation.  ...  The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL).  ...  We thank Carl Doersch, Raia Hadsell, Karl Moritz Hermann, Mateusz Malinowski, and Andrew Zisserman for their discussions and contributions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.05930v2">arXiv:1906.05930v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mwf5brjotzedrk2ll4ibypv5cq">fatcat:mwf5brjotzedrk2ll4ibypv5cq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901095010/https://arxiv.org/pdf/1906.05930v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7c/04/7c04f9218bd187cb8bcb694caf460cd5395eb840.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.05930v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning [article]

Ting Wang, Zongkai Wu, Donglin Wang
<span title="2021-01-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
One of them uses the Model-Agnostic Meta-Learning (MAML) algorithm that requires a few shot adaptation, and the other refers to a metric-based meta-learning method with a feature-wise affine transformation  ...  The experiment results show that our strategy successfully adapts the learned navigation model to a new camera configuration, and the two algorithms show their advantages in seen and unseen environments  ...  Experiments for MAML For adaptation with MAML [], our algorithm implementation uses the same inner learning rate of 2e − 4 and outer learning rate of 2e − 4, three-shots, ten gradient step updates, and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05446v3">arXiv:2012.05446v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/exil5a3htvdxldddgox6jgaqmm">fatcat:exil5a3htvdxldddgox6jgaqmm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201215070054/https://arxiv.org/pdf/2012.05446v2.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/89/e0/89e0f0efc8ced83b90f0caa9825277b15e179e29.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.05446v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Cross-View Policy Learning for Street Navigation

Ang Li, Huiyi Hu, Piotr Mirowski, Mehrdad Farajtabar
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/753trptklbb4nj6jquqadzwwdu" style="color: black;">2019 IEEE/CVF International Conference on Computer Vision (ICCV)</a> </i> &nbsp;
called StreetLearn and used for research on navigation.  ...  The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL).  ...  We thank Carl Doersch, Raia Hadsell, Karl Moritz Hermann, Mateusz Malinowski, and Andrew Zisserman for their discussions and contributions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2019.00819">doi:10.1109/iccv.2019.00819</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccv/LiHMF19.html">dblp:conf/iccv/LiHMF19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ksrgdrjhpvcqpjgq7qtijofe4a">fatcat:ksrgdrjhpvcqpjgq7qtijofe4a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710063705/https://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Cross-View_Policy_Learning_for_Street_Navigation_ICCV_2019_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f1/7c/f17c6aefb2e91106169b0ae4122bc7e3fc7e6780.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2019.00819"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey [article]

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths
<span title="2020-05-25">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, we discuss several challenges and future topics for using adversarial learning, RL and meta-learning in autonomous systems.  ...  Here, we review the learning-based approaches in autonomous systems from the perspectives of accuracy and transferability.  ...  The model combines appearance adaptation networks and representation adaptation networks to synthesize images for domain adaptation at both the visual appearance-level and the representation-level.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12948v3">arXiv:2003.12948v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qtmjs74p2vh6thdotbhgebdvoi">fatcat:qtmjs74p2vh6thdotbhgebdvoi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829050013/https://arxiv.org/pdf/2003.12948v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e4/be/e4be9d631388e677390a70c768712da25b6f629f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12948v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Mitchell Wortsman, Kiana Ehsani, Mohammad Rastegari, Ali Farhadi, Roozbeh Mottaghi
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes.  ...  Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings.  ...  We also thank Luca Weihs and Eric Kolve for their help with setting up the framework, Winson Han for his help with figures, and Chelsea Finn for her valuable suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00691">doi:10.1109/cvpr.2019.00691</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/WortsmanERFM19.html">dblp:conf/cvpr/WortsmanERFM19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p47g6s72vrd2bcrhhhd5tpbhwe">fatcat:p47g6s72vrd2bcrhhhd5tpbhwe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200319050610/http://openaccess.thecvf.com/content_CVPR_2019/papers/Wortsman_Learning_to_Learn_How_to_Learn_Self-Adaptive_Visual_Navigation_Using_CVPR_2019_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4d/21/4d21334ea3564c89586e1ba176e11382bdd3d394.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00691"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

State-based SHOSLIF for indoor visual navigation

Juyang Weng, Shaoyun Chen
<span title="">2000</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/22mhkeaq5zdqlmtti5oidj26fi" style="color: black;">IEEE Transactions on Neural Networks</a> </i> &nbsp;
His current research interests include mental development, computer vision, autonomous navigation, human-machine interface using vision, speech, gesture, and actions.  ...  with their environments, including human teachers, using their sensors and effectors.  ...  Set B A full set of 318 (30 40)-pixel real images. This set of images was used in our training of SHOSLIF-N for vision-based navigation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/72.883430">doi:10.1109/72.883430</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/18249855">pmid:18249855</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bpv642bd5vcwldovkn4mmjvela">fatcat:bpv642bd5vcwldovkn4mmjvela</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829231444/http://www.sc.ehu.es/ccwgrrom/transparencias/articulos-alumnos-doct-2002/felipe-martin/00883430.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c1/cf/c1cfb14e6bc094a3685b366309d9bdd9664f2dcc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/72.883430"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning [article]

Mitchell Wortsman, Kiana Ehsani, Mohammad Rastegari, Ali Farhadi, Roozbeh Mottaghi
<span title="2019-03-26">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experiments, performed in the AI2-THOR framework, show major improvements in both success rate and SPL for visual navigation in novel scenes.  ...  Learning how to learn and adapt is a key property that enables us to generalize effortlessly to new settings.  ...  We also thank Luca Weihs and Eric Kolve for their help with setting up the framework, Winson Han for his help with figures, and Chelsea Finn for her valuable suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.00971v2">arXiv:1812.00971v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/365y55ybwrh7jf3aydosco5kge">fatcat:365y55ybwrh7jf3aydosco5kge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825214203/https://arxiv.org/pdf/1812.00971v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0b/8e/0b8ece73abe140d36d499cfc40ecc83dd8b61f45.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.00971v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 127,400 results