Filters








518,976 Hits in 2.6 sec

Visualizing Transfer Learning [article]

Róbert Szabó, Dániel Katona, Márton Csillag, Adrián Csiszárik, Dániel Varga
<span title="2020-07-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We provide visualizations of individual neurons of a deep image recognition network during the temporal process of transfer learning.  ...  image features, and behavior of transfer learning to small data.  ...  Visualization of transfer learning from ImageNet to CelebA at different layer depths.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.07628v1">arXiv:2007.07628v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ej326ne33vdpvm6yzrfccbfxci">fatcat:ej326ne33vdpvm6yzrfccbfxci</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200717103932/https://arxiv.org/pdf/2007.07628v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.07628v1" 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>

Robust visual tracking via transfer learning

Wenhan Luo, Xi Li, Wei Li, Weiming Hu
<span title="">2011</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/anlh4tvwprcrtoxv5d4h6a7rye" style="color: black;">2011 18th IEEE International Conference on Image Processing</a> </i> &nbsp;
In this paper, we propose a boosting based tracking framework using transfer learning.  ...  To deal with complex appearance variations, the proposed tracking framework tries to utilize discriminative information from previous frames to conduct the tracking task in the current frame, and thus transfers  ...  A randomized learning technique called Random Forests is developed in [7] to select features online for visual tracking.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2011.6116557">doi:10.1109/icip.2011.6116557</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icip/LuoLLH11.html">dblp:conf/icip/LuoLLH11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uc244ev7kvh3bfdaqk7uucn5zy">fatcat:uc244ev7kvh3bfdaqk7uucn5zy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808124409/http://www.nlpr.ia.ac.cn/2011papers/gjhy/gh109.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/f4/02/f40280dd23a8a3f3634f856a6b4991426d8d5c71.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icip.2011.6116557"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Developmental Bayesian Optimization of Black-Box with Visual Similarity-Based Transfer Learning [article]

Maxime Petit, Xiaofang Wang
<span title="2018-10-19">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In simulation, we demonstrate the benefit of the transfer learning based on visual similarity, as opposed to an amnesic learning (i.e. learning from scratch all the time).  ...  The learning can take advantage of past experiences (stored in the episodic and procedural memories) in order to warm-start the exploration using a set of hyper-parameters previously optimized from objects  ...  arXiv:1809.10141v7 [cs.RO] 19 Oct 2018 Robot learning phase (without Transfert Learning) Addi�onal flow when Transfer Learning based on Visual Similarity Long-Term Memory Episodic Memory Seman�c Memory  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.10141v7">arXiv:1809.10141v7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/o7efubhzj5dwnmzhsyvcw7vdra">fatcat:o7efubhzj5dwnmzhsyvcw7vdra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930020621/https://arxiv.org/pdf/1809.10141v7.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/55/80/5580ef47313e06353c8ace3f36ac241d1f717c43.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.10141v7" 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>

Big Transfer (BiT): General Visual Representation Learning [article]

Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Joan Puigcerver, Jessica Yung, Sylvain Gelly, Neil Houlsby
<span title="2020-05-05">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
BiT achieves 87.5% top-1 accuracy on ILSVRC-2012, 99.4% on CIFAR-10, and 76.3% on the 19 task Visual Task Adaptation Benchmark (VTAB).  ...  We scale up pre-training, and propose a simple recipe that we call Big Transfer (BiT).  ...  Li, A., Jabri, A., Joulin, A., van der Maaten, L.: Learning visual n-grams from web data. In: ICCV (2017) 31.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.11370v3">arXiv:1912.11370v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oesjnhydwvbtfarsssmn5a2p7m">fatcat:oesjnhydwvbtfarsssmn5a2p7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200528072755/https://arxiv.org/pdf/1912.11370v3.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/bc/51/bc51622358d8eea83248ef29402fe10640d07ba6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1912.11370v3" 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>

Transfer of object learning across distinct visual learning paradigms

Annelies Baeck
<span title="">2010</span> <i title="Association for Research in Vision and Ophthalmology (ARVO)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rahwjcylyzhtlni57joehivgqm" style="color: black;">Journal of Vision</a> </i> &nbsp;
Perception of visual stimuli improves with experience. For objects, learning is specific for the stimuli used during training.  ...  This is shown in perceptual learning paradigms in which visual perception is challenged by degrading the stimuli, e.g. by backward masking or adding simultaneous noise.  ...  The results with respect to a transfer in performance between the distinct visual learning paradigms were asymmetric.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1167/10.2.17">doi:10.1167/10.2.17</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/20462318">pmid:20462318</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/32vjdbugxvgovc6s6zilnk7i7a">fatcat:32vjdbugxvgovc6s6zilnk7i7a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190303064022/http://pdfs.semanticscholar.org/b0fe/68596041ee5b0561267c1ab2258b3d66b853.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/b0/fe/b0fe68596041ee5b0561267c1ab2258b3d66b853.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1167/10.2.17"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Transfer of object learning across distinct visual learning paradigms

A. Baeck, H. Op de Beeck
<span title="2010-08-13">2010</span> <i title="Association for Research in Vision and Ophthalmology (ARVO)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rahwjcylyzhtlni57joehivgqm" style="color: black;">Journal of Vision</a> </i> &nbsp;
Perception of visual stimuli improves with experience. For objects, learning is specific for the stimuli used during training.  ...  This is shown in perceptual learning paradigms in which visual perception is challenged by degrading the stimuli, e.g. by backward masking or adding simultaneous noise.  ...  The results with respect to a transfer in performance between the distinct visual learning paradigms were asymmetric.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1167/10.7.1154">doi:10.1167/10.7.1154</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bb5up6dc75bvpfrkr7bijss5iy">fatcat:bb5up6dc75bvpfrkr7bijss5iy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170829004026/http://jov.arvojournals.org/data/journals/jov/932794/jov-10-2-17.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/fe/f1fea59842b348335d1d202b410e7d37e24312bd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1167/10.7.1154"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Learning Visual Representations for Transfer Learning by Suppressing Texture [article]

Shlok Mishra, Anshul Shah, Ankan Bansal, Jonghyun Choi, Abhinav Shrivastava, Abhishek Sharma, David Jacobs
<span title="2020-11-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our method is particularly effective for transfer learning tasks and we observed improved performance on five standard transfer learning datasets.  ...  better transfer.  ...  We show results of transfer learning on some the datasets that were used by Kornblith et al. (2019) . METHODS Texture and other visual cues may bias CNNs towards over-fitting on these cues.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.01901v2">arXiv:2011.01901v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ncpzsmjgifhbhgdqpjrcbdb4ai">fatcat:ncpzsmjgifhbhgdqpjrcbdb4ai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108201913/https://arxiv.org/pdf/2011.01901v2.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/dc/73/dc73e4bc71ec6e981d08fcb69952bebd9e5e538a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.01901v2" 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>

Transfer Learning in Visual and Relational Reasoning [article]

T.S. Jayram and Vincent Marois and Tomasz Kornuta and Vincent Albouy and Emre Sevgen and Ahmet S. Ozcan
<span title="2020-02-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In visual reasoning tasks, such as image question answering, transfer learning is more complex.  ...  In this work, we formalize these unique aspects of transfer learning and propose a theoretical framework for visual reasoning, exemplified by the well-established CLEVR and COG datasets.  ...  Transfer Learning Due to the complex nature of visual reasoning, it appears that transfer learning from a source domain to a target domain can be investigated in multiple ways, depending on how the two  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.11938v2">arXiv:1911.11938v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/25t6dzscbbdqjdv3uymvhv66o4">fatcat:25t6dzscbbdqjdv3uymvhv66o4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321174633/https://arxiv.org/pdf/1911.11938v2.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.11938v2" 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>

Transfer Learning Based Image Visualization Using CNN

Santosh Giri, Basanta Joshi
<span title="2019-07-31">2019</span> <i title="Academy and Industry Research Collaboration Center (AIRCC)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dlcgzkn4cvbevhkswphjjxglsa" style="color: black;">International Journal of Artificial Intelligence &amp; Applications</a> </i> &nbsp;
By using the transfer learning mechanism the classification layer of the CNN model was trained with 20 classes of Caltech101 image dataset and 17 classes of Oxford 17 flower image dataset.  ...  Image classification is a popular machine learning based applications of deep learning.  ...  To retrain the classification layer we implement the transfer learning [30] Cnn Model Design Transfer Learning Inception v3 [6] is a convolutional neural network model and by using GPU configured  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5121/ijaia.2019.10404">doi:10.5121/ijaia.2019.10404</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oaqq4ietwbe3vazbt2r2uiferu">fatcat:oaqq4ietwbe3vazbt2r2uiferu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191114232438/http://aircconline.com/ijaia/V10N4/10419ijaia04.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/e1/ce/e1ceb22f87c35468b5d12540264eece94e26b447.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5121/ijaia.2019.10404"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Visual Interest Prediction with Attentive Multi-Task Transfer Learning [article]

Deepanway Ghosal, Maheshkumar H. Kolekar
<span title="2020-05-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a transfer learning and attention mechanism based neural network model to predict visual interest & affective dimensions in digital photos.  ...  Visual interest & affect prediction is a very interesting area of research in the area of computer vision.  ...  Conclusion In this work we proposed an attention based multi-task transfer learning model for multi-dimensional visual affect prediction in digital photos.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.12770v2">arXiv:2005.12770v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h2q2c4qoqvdzpitzig3tenl4ha">fatcat:h2q2c4qoqvdzpitzig3tenl4ha</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200529045047/https://arxiv.org/pdf/2005.12770v2.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.12770v2" 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>

Category-Induced Transfer of Visual Perceptual Learning

Qingleng Tan, Zhiyan Wang, Yuka Sasaki, Takeo Watanabe
<span title="2019-03-28">2019</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/waxwzq3cnbet3cmwccpuk4bel4" style="color: black;">Current Biology</a> </i> &nbsp;
Furthermore, we found that, although category learning transferred to other locations in the visual field, the category-induced transfer of VPL occurred only when visual stimuli for the category learning  ...  Visual perceptual learning (VPL) refers to a long-term enhancement of visual task performance as a result of visual experience [1-6].  ...  •Perceptual learning transferred to features within the same category as the trained • Category learning of orientations transferred to the opposite visual hemifield.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cub.2019.03.003">doi:10.1016/j.cub.2019.03.003</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30930042">pmid:30930042</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6482054/">pmcid:PMC6482054</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qskaitkxe5az7p4yidubnujpai">fatcat:qskaitkxe5az7p4yidubnujpai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200502085506/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC6482054&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/e0/78/e078515a0b1bda35298b92a1aff997a4787ec1ab.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cub.2019.03.003"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6482054" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Learning Transferable UAV for Forest Visual Perception

Lyujie Chen, Wufan Wang, Jihong Zhu
<span title="">2018</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
To transfer the learned strategy to the real world, we construct a ResNet-18 adaptation model via multi-kernel maximum mean discrepancies to leverage the relevant labelled data and alleviate the discrepancy  ...  Then we formulate visual perception of forests as a classification problem. A ResNet-18 model is trained to decide the moving direction frame by frame.  ...  Transfer Learning Transfer learning focuses on applying knowledge gained from solved problems to a different but related problem [Weiss et al., 2016] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/678">doi:10.24963/ijcai.2018/678</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/ChenWZ18.html">dblp:conf/ijcai/ChenWZ18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gk7w577mhnc7nekq2wao2kldsy">fatcat:gk7w577mhnc7nekq2wao2kldsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190429114049/https://www.ijcai.org/proceedings/2018/0678.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/d5/28/d528ff180ea64053acf83fb80daff4503bd1a9ca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2018/678"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Learning Transferable UAV for Forest Visual Perception [article]

Lyujie Chen, Wufan Wang, Jihong Zhu
<span title="2018-06-10">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To transfer the learned strategy to the real world, we construct a ResNet-18 adaptation model via multi-kernel maximum mean discrepancies to leverage the relevant labelled data and alleviate the discrepancy  ...  Then we formulate visual perception of forests as a classification problem. A ResNet-18 model is trained to decide the moving direction frame by frame.  ...  Transfer Learning Transfer learning focuses on applying knowledge gained from solved problems to a different but related problem [Weiss et al., 2016] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.03626v1">arXiv:1806.03626v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wq62hc4snfatporl5xui4jtnqa">fatcat:wq62hc4snfatporl5xui4jtnqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191019144329/https://arxiv.org/pdf/1806.03626v1.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/8f/52/8f52080bbce60d099bcf7303c9084954d077972e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.03626v1" 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 Transfer Visual Effects from Videos to Images [article]

Christopher Thomas, Yale Song, Adriana Kovashka
<span title="2020-12-17">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We study the problem of animating images by transferring spatio-temporal visual effects (such as melting) from a collection of videos.  ...  We tackle two primary challenges in visual effect transfer: 1) how to capture the effect we wish to distill; and 2) how to ensure that only the effect, rather than content or artistic style, is transferred  ...  Our models may have learned to transfer the visual effect faster or slower than the souce video.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.01642v2">arXiv:2012.01642v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5x3hlh4qebdj5owkmkhycfnnuu">fatcat:5x3hlh4qebdj5owkmkhycfnnuu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201206040704/https://arxiv.org/pdf/2012.01642v1.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/18/d0/18d083bc4180a2fd3d32892c3c190e9fd5a16bfc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.01642v2" 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>

A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification [article]

Uddipan Mukherjee, Sidharth Pancholi
<span title="2021-10-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This research proposes to convert cleansed and normalized heart sound into visual mel scale spectrograms and then using visual domain transfer learning approaches to automatically extract features and  ...  Some of the previous studies found that the spectrogram of various types of heart sounds is visually distinguishable to human eyes, which motivated this study to experiment on visual domain classification  ...  Transfer Learning Transfer learning was conceptualized by taking inspiration from the human learning process.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.13237v2">arXiv:2107.13237v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w5u2xass6bhgjohnbrxebkedam">fatcat:w5u2xass6bhgjohnbrxebkedam</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211006114537/https://arxiv.org/pdf/2107.13237v2.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/77/27/7727be20227ff833cc1d0231775aa4502e9eabb0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.13237v2" 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 518,976 results