Filters








4,200 Hits in 7.1 sec

Semi-supervised learning using multiple one-dimensional embedding based adaptive interpolation

Jianzhong Wang
<span title="">2016</span> <i title="World Scientific Pub Co Pte Lt"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nt43ge63cnbllg3y2b3kw6sx4a" style="color: black;">International Journal of Wavelets, Multiresolution and Information Processing</a> </i> &nbsp;
We propose a novel semi-supervised learning scheme using adaptive interpolation on multiple one-dimensional (1-D) embedded data.  ...  Repeating the embedding and interpolation, we enlarge the labeled subset gradually, and finally reach a labeled set with a reasonable large size, based on which the final classifier is constructed.  ...  Based on the multiple 1-D embedding model, we propose the Multiple One-Dimensional Embedding Based Adaptive Interpolation (M1DEI) for semi-supervised learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1142/s0219691316400026">doi:10.1142/s0219691316400026</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tzerktvyknafpgsi6coabshjqe">fatcat:tzerktvyknafpgsi6coabshjqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190220185249/http://pdfs.semanticscholar.org/2689/b150a5d538f4e96d364b92d1a47c6199621c.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/26/89/2689b150a5d538f4e96d364b92d1a47c6199621c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1142/s0219691316400026"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> worldscientific.com </button> </a>

Achieving Multi-Accent ASR via Unsupervised Acoustic Model Adaptation

M.A. Tuğtekin Turan, Emmanuel Vincent, Denis Jouvet
<span title="2020-10-25">2020</span> <i title="ISCA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2020</a> </i> &nbsp;
In addition, we leverage untranscribed accented training data by means of semi-supervised learning.  ...  Semi-supervised training using just 1 hour of untranscribed speech per accent yields an additional 15% relative WER reduction w.r.t. models trained on native data only.  ...  Semi-Supervised Learning Independently from on-the-fly adaptation, any non-native or accented speech data available at training time (including the data used to train the embeddings) can be leveraged for  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2020-2742">doi:10.21437/interspeech.2020-2742</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/Turan0J20.html">dblp:conf/interspeech/Turan0J20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yw6dswposzbdxet5wpmfbp433y">fatcat:yw6dswposzbdxet5wpmfbp433y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201212132755/https://www.isca-speech.org/archive/Interspeech_2020/pdfs/2742.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/de/4d/de4d6ea8bfb0466234d4166dce3f155a14601eb2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2020-2742"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A Fast Radio Map Construction Method Merging Self-Adaptive Local Linear Embedding (LLE) and Graph-Based Label Propagation in WLAN Fingerprint Localization Systems

Ni, Chai, Wang, Fang
<span title="2020-01-30">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
First, this method uses the self-adaptive local linear embedding (SLLE) algorithm based on manifold learning to reduce the dimension of the high-dimensional RSSI samples and to extract a neighbor weight  ...  To solve the problem, this paper proposes a semi-supervised self-adaptive local linear embedding algorithm to build the radio map.  ...  This includes methods based on crowdsourcing [5, 6] , semi-supervised learning [7, 8, 9] or unsupervised learning [10, 11] , the path loss model [12, 13] , interpolation [14, 15] , and the merging  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s20030767">doi:10.3390/s20030767</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/32019229">pmid:32019229</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7038483/">pmcid:PMC7038483</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5ag3c6etyff3zadcladxboi7ze">fatcat:5ag3c6etyff3zadcladxboi7ze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209054927/https://res.mdpi.com/d_attachment/sensors/sensors-20-00767/article_deploy/sensors-20-00767.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/b7/34/b734e2944b12833bfc11c6a82fe3bdcbada0811a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s20030767"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7038483" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Hybrid Consistency Training with Prototype Adaptation for Few-Shot Learning [article]

Meng Ye, Xiao Lin, Giedrius Burachas, Ajay Divakaran, Yi Yao
<span title="2020-11-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
As for the second challenge, we use unlabeled examples to iteratively normalize features and adapt prototypes, as opposed to commonly used one-time update, for more reliable prototype-based transductive  ...  data augmentation consistency that learns robust embeddings against sample variations.  ...  Borrowing ideas from semi-supervised learning, our HCT combines interpolation and data augmentation consistency and applies these consistency-based losses on labeled data from base classes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.10082v1">arXiv:2011.10082v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7du7zhyhkvedlp4geiyousaalm">fatcat:7du7zhyhkvedlp4geiyousaalm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201124042646/https://arxiv.org/pdf/2011.10082v1.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/b7/3b/b73b130084c20349d84f9fca5588a33688658d36.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.10082v1" 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>

Nonlinear Supervised Dimensionality Reduction via Smooth Regular Embeddings [article]

Cem Ornek, Elif Vural
<span title="2018-05-28">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we build on recent theoretical results on the generalization performance of supervised manifold learning algorithms.  ...  Motivated by these performance bounds, we propose a supervised manifold learning method that computes a nonlinear embedding while constructing a smooth and regular interpolation function that extends the  ...  Several supervised linear dimensionality reduction methods are based on preserving locally linear representations of data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1710.07120v2">arXiv:1710.07120v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hwe46a53mnbivb5cgpzpubzmlq">fatcat:hwe46a53mnbivb5cgpzpubzmlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191017085018/https://arxiv.org/pdf/1710.07120v2.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/e6/3a/e63a0ea338dfc7293ddd68074baf250e99d0c6d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1710.07120v2" 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>

Infinite Mixture Prototypes for Few-Shot Learning [article]

Kelsey R. Allen, Evan Shelhamer, Hanul Shin, Joshua B. Tenenbaum
<span title="2019-02-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning.  ...  In clustering labeled and unlabeled data by the same clustering rule, infinite mixture prototypes achieves state-of-the-art semi-supervised accuracy.  ...  IMP learns a deep embedding while also adapting the model capacity based on the complexity of the embedded data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.04552v1">arXiv:1902.04552v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mmillrfyqjduxb5vutjwcmiwrm">fatcat:mmillrfyqjduxb5vutjwcmiwrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828230000/https://arxiv.org/pdf/1902.04552v1.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/10/f7/10f7b1e413462765c7ae12ca4d8ae65a0930054a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.04552v1" 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>

Unsupervised Learning via Meta-Learning [article]

Kyle Hsu and Sergey Levine and Chelsea Finn
<span title="2019-03-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics.  ...  Surprisingly, we find that, when integrated with meta-learning, relatively simple task construction mechanisms, such as clustering embeddings, lead to good performance on a variety of downstream, human-specified  ...  ACKNOWLEDGMENTS We thank Kelvin Xu, Richard Zhang, Brian Cheung, Ben Poole, Aäron van den Oord, Luke Metz, Siddharth Reddy, and the anonymous reviewers for feedback on an early draft of this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02334v6">arXiv:1810.02334v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b5xxbul44zegjac3mjvspqnlka">fatcat:b5xxbul44zegjac3mjvspqnlka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191021220726/https://arxiv.org/pdf/1810.02334v6.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/f4/7a/f47a3b9ba14e205d6d7b755c81db515d6a46f963.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.02334v6" 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>

Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings [article]

Viraj Prabhu, Arjun Chandrasekaran, Kate Saenko, Judy Hoffman
<span title="2021-10-10">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We demonstrate how existing AL approaches based solely on model uncertainty or diversity sampling are less effective for Active DA.  ...  CLUE consistently outperforms competing label acquisition strategies for Active DA and AL across learning settings on 6 diverse domain shifts for image classification.  ...  We would like to thank Devi Parikh for guidance, and Prithvijit Chattopadhyay, Cornelia Köhler, and Shruti Venkatram for feedback on the draft.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08666v3">arXiv:2010.08666v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p3tcvwu23bccxazc3ohfgf2sc4">fatcat:p3tcvwu23bccxazc3ohfgf2sc4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211014232940/https://arxiv.org/pdf/2010.08666v3.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/f8/1a/f81ad506ad2e66793bfb2b0c4ca3627ab0fbe51c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08666v3" 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>

Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization [article]

Marin Scalbert, Maria Vakalopoulou, Florent Couzinié-Devy
<span title="2021-09-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Multi-Source Unsupervised Domain Adaptation (multi-source UDA) aims to learn a model from several labeled source domains while performing well on a different target domain where only unlabeled data are  ...  Simultaneously, interpolated source examples are leveraged to align source class conditional distributions through an interpolated version of the supervised contrastive loss.  ...  Semi-supervised learning. To exploit unlabeled examples, common semi-supervised approaches are based either on consistency regularization [2, 21, 31, 41] or pseudo labeling [1] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.16093v3">arXiv:2106.16093v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kyeg2uatyfcthiamczwsie3m3i">fatcat:kyeg2uatyfcthiamczwsie3m3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211002150943/https://arxiv.org/pdf/2106.16093v3.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/4b/07/4b07292f9ce297256118f8758ada85f83285bf08.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.16093v3" 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>

Unsupervised Feature Learning of Human Actions as Trajectories in Pose Embedding Manifold [article]

Jogendra Nath Kundu, Maharshi Gor, Phani Krishna Uppala, R. Venkatesh Babu
<span title="2018-12-06">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Further, we show the qualitative strengths of the proposed framework by visualizing skeleton pose reconstructions and interpolations in pose-embedding space, and low dimensional principal component projections  ...  We demonstrate state-of-the-art transfer-ability of the learned representation against other supervisedly and unsupervisedly learned motion embeddings for the task of fine-grained action recognition on  ...  Here, semi-supervised refers to use of semi-supervisedly learned motion embedding in contrast to the previous unsupervised setting.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.02592v1">arXiv:1812.02592v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/37jnz4444faudnvaiao5d6sjym">fatcat:37jnz4444faudnvaiao5d6sjym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200824230226/https://arxiv.org/pdf/1812.02592v1.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/b9/e3/b9e32421a6a8b0c0ad0a0c9d1c8be2aed9fde267.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.02592v1" 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>

Semi-Supervised Learning-Based Image Denoising for Big Data

Kun Zhang, Kai Chen
<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 this paper, the research of image noise reduction based on semi-supervised learning is carried out, and the neural network is used to reduce the noise of the image, so as to achieve more stable and  ...  Semi-supervised residual learning based on convolutional network is a good image denoising and denoising network model. Compared with other excellent denoising algorithms, it has very good results.  ...  CONCLUSION This paper mainly studies a denoising algorithm based on improved semi-supervised learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3025324">doi:10.1109/access.2020.3025324</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tumqijargbgovpdmwo6t5r4yn4">fatcat:tumqijargbgovpdmwo6t5r4yn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108013817/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09201398.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/a1/68/a1689c3137428f7a58b761a5a4b89db9c278f8b2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3025324"> <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>

Multi-velocity neural networks for gesture recognition in videos [article]

Otkrist Gupta, Dan Raviv, Ramesh Raskar
<span title="2016-03-22">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We further provide the training steps for our semi-supervised network, suited to learn from huge unlabeled datasets with only a fraction of labeled examples.  ...  We present a new action recognition deep neural network which adaptively learns the best action velocities in addition to the classification.  ...  Grassman kernel based multiple kernel approaches 9.09 17.9 44.99 Expressionlets based manifold learning techniques 52.91 82.7 48.6 Our Methods Semi-Supervised Learner for gesture classification  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.06829v1">arXiv:1603.06829v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rrnpzmmhqrbtfml77pzo22apdy">fatcat:rrnpzmmhqrbtfml77pzo22apdy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200918003556/https://arxiv.org/pdf/1603.06829v1.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/a4/87/a4876b7493d8110d4be720942a0f98c2d116d2a0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1603.06829v1" 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>

Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions [article]

Han-Jia Ye and Hexiang Hu and De-Chuan Zhan and Fei Sha
<span title="2021-06-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We denote this model as FEAT (few-shot embedding adaptation w/ Transformer) and validate it on both the standard few-shot classification benchmark and four extended few-shot learning settings with essential  ...  use cases, i.e., cross-domain, transductive, generalized few-shot learning, and low-shot learning.  ...  We further study this semi-supervised learning setting to see how well FEAT can incorporate test instances into joint embedding adaptation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.03664v6">arXiv:1812.03664v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rkllpdlgsjfmrbrhdcvgcqtu6y">fatcat:rkllpdlgsjfmrbrhdcvgcqtu6y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200402013037/https://arxiv.org/pdf/1812.03664v5.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/bd/54/bd54a60455455e1dc71a344bdba5885f33e7890a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.03664v6" 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>

Filtered Manifold Alignment [article]

Stefan Dernbach, Don Towsley
<span title="2020-11-11">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present a new semi-supervised manifold alignment technique based on a two-step approach of projecting and filtering the source and target domains to low dimensional spaces followed by  ...  Domain adaptation is an essential task in transfer learning to leverage data in one domain to bolster learning in another domain.  ...  This work introduces a new semi-supervised filtered manifold alignment (FMA) technique in which we align two datasets by first learning an individual embedding for each domain based on a discrete graph  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.05716v1">arXiv:2011.05716v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7723yrufazghdf7v7mfmtn3tgy">fatcat:7723yrufazghdf7v7mfmtn3tgy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201113032118/https://arxiv.org/pdf/2011.05716v1.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/ef/c8/efc8939a9537c28c38689a663e53d8c7dd930158.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.05716v1" 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>

3D Point Capsule Networks [article]

Yongheng Zhao and Tolga Birdal and Haowen Deng and Federico Tombari
<span title="2019-07-11">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, it enables new applications such as part interpolation and replacement.  ...  Semi-supervision guides the capsules to meaningful parts We now consider the effect of training in steering the capsules towards the optimal solution in the task of supervised part segmentation.  ...  [1] adapted GANs to 3D point sets paving the way to enhanced generative learning. 2D Capsule Networks Thanks to their general applicability, capsule networks (CNs) have found tremendous use in 2D deep  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.10775v2">arXiv:1812.10775v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3s4izwmtknejdiwfonccobtmru">fatcat:3s4izwmtknejdiwfonccobtmru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827094539/https://arxiv.org/pdf/1812.10775v1.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/f9/8c/f98c4184b625116c696f5c80db5128ae27e1dd6b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.10775v2" 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 4,200 results