Filters








5,318 Hits in 7.4 sec

Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces [article]

Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R. Gormley, Graham Neubig
<span title="2019-08-19">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and  ...  a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.  ...  Sup, Unsup and Semi refer to supervised, unsupervised and semi-supervised methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.06625v1">arXiv:1908.06625v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qsiyj3wthbbapbkwbojuvojxou">fatcat:qsiyj3wthbbapbkwbojuvojxou</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907045922/https://arxiv.org/pdf/1908.06625v1.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/9e/d9/9ed9f521d4102774e121b31dd5bdaac9656bd62f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.06625v1" 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>

Variational Information Bottleneck Model for Accurate Indoor Position Recognition [article]

Weizhu Qian, Franck Gechter
<span title="2021-01-26">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we solve this issue by combining the Information Bottleneck method and Variational Inference.  ...  We conduct the validation experiments on a real-world dataset. We also compare the proposed model to other existing methods so as to quantify the performances of our method.  ...  However, in our study, we find that leveraging the Information Bottleneck method to this problem is a better option than the semi-VAE model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.10655v1">arXiv:2101.10655v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zbk7wtobpvbynpejq55ydugo7e">fatcat:zbk7wtobpvbynpejq55ydugo7e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210130204115/https://arxiv.org/pdf/2101.10655v1.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/9c/cd/9ccd872ad39faa040a1873bf314d34dddfef4c85.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.10655v1" 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>

CycleCluster: Modernising Clustering Regularisation for Deep Semi-Supervised Classification [article]

Philip Sellars, Angelica Aviles-Rivero, Carola Bibiane Schönlieb
<span title="2021-09-01">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a novel framework, CycleCluster, for deep semi-supervised classification.  ...  Given the potential difficulties in obtaining large quantities of labelled data, many works have explored the use of deep semi-supervised learning, which uses both labelled and unlabelled data to train  ...  SUPPLEMENTARY MATERIAL In this section we provide supplementary material for our CycleCluster methods that proposes and explores cluster regularisation for semi-supervised image classification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.05317v2">arXiv:2001.05317v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ispbyuphojgxtfvyzolzpxki74">fatcat:ispbyuphojgxtfvyzolzpxki74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210904182426/https://arxiv.org/pdf/2001.05317v2.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/40/eb/40ebf52476daea1a26614b407d78816d542a0656.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.05317v2" 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 Survey on Deep Hashing Methods

Xiao Luo, Haixin Wang, Daqing Wu, Chong Chen, Minghua Deng, Jianqiang Huang, Xian-Sheng Hua
<span title="2022-04-27">2022</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/gvg3htf2zjex5j7pnaz4tzal6a" style="color: black;">ACM Transactions on Knowledge Discovery from Data</a> </i> &nbsp;
Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining  ...  We also introduce three related important topics including semi-supervised deep hashing, domain adaption deep hashing and multi-modal deep hashing.  ...  Deep supervised hashing has been explored over a long period.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3532624">doi:10.1145/3532624</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7lxtu2qzvvhrpnjngefli2mvca">fatcat:7lxtu2qzvvhrpnjngefli2mvca</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220428201215/https://dl.acm.org/doi/pdf/10.1145/3532624" 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/ed/deed3b0f06da8201ac99252ce3b9a6b82c582da2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3532624"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Self-Taught Semi-Supervised Anomaly Detection on Upper Limb X-rays [article]

Antoine Spahr, Behzad Bozorgtabar, Jean-Philippe Thiran
<span title="2021-02-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Through extensive experiments, we show that our method outperforms baselines across unsupervised and self-supervised anomaly detection settings on a real-world medical dataset, the MURA dataset.  ...  Supervised deep networks take for granted a large number of annotations by radiologists, which is often prohibitively very time-consuming to acquire.  ...  We explored two extensions of deep semi-supervised anomaly detection (DSAD) [22] (a joint training of the AE and the hyper-sphere, an alternative distance metric for the anomaly score) and an adversarially  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09895v2">arXiv:2102.09895v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nzf4mmcqyrcutafxr4jhtobalu">fatcat:nzf4mmcqyrcutafxr4jhtobalu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210223021348/https://arxiv.org/pdf/2102.09895v1.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/75/02/75022afd1a297ce4d18c16a12ed83f50e471e615.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09895v2" 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 Survey on Deep Hashing Methods [article]

Xiao Luo, Haixin Wang, Daqing Wu, Chong Chen, Minghua Deng, Jianqiang Huang, Xian-Sheng Hua
<span title="2022-04-23">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining  ...  We also introduce three related important topics including semi-supervised deep hashing, domain adaption deep hashing and multi-modal deep hashing.  ...  Deep supervised hashing has been explored over a long period.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03369v5">arXiv:2003.03369v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m2iu3htilvgztkcazw3cyk6iqe">fatcat:m2iu3htilvgztkcazw3cyk6iqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220504192556/https://arxiv.org/pdf/2003.03369v5.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/50/d9/50d93acf27127fe472e859d508adacf6c829b226.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.03369v5" 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>

Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces

Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R. Gormley, Graham Neubig
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</a> </i> &nbsp;
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) -a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and  ...  a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.  ...  Sup, Unsup and Semi refer to supervised, unsupervised and semi-supervised methods.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1018">doi:10.18653/v1/p19-1018</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/PatraMGGN19.html">dblp:conf/acl/PatraMGGN19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ec66dua2xnbajk3fbmccsl7wwe">fatcat:ec66dua2xnbajk3fbmccsl7wwe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508214031/https://www.aclweb.org/anthology/P19-1018.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/db/1d/db1dafd0c356491cbbf53338b9984de324e7239c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1018"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

An Insight into Word Sense Disambiguation Techniques

Harsimran Singh, Vishal Gupta
<span title="2015-05-20">2015</span> <i title="Foundation of Computer Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b637noqf3vhmhjevdfk3h5pdsu" style="color: black;">International Journal of Computer Applications</a> </i> &nbsp;
There are a number of techniques such as: Knowledge based approaches, which use the knowledge encoded in Lexical resources; Supervised Machine Leaning methods in which the classifier is made to learn from  ...  Then there are also semi supervised approaches which use semi annotated corpus as reference data along with unlabeled data.  ...  Semi-supervised or minimally supervised approaches lie midway between supervised and unsupervised approaches.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/20888-3666">doi:10.5120/20888-3666</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/igoikbgvavfetfptwinwbz5z7y">fatcat:igoikbgvavfetfptwinwbz5z7y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170814082604/http://research.ijcaonline.org/volume118/number23/pxc3903666.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/aa/0d/aa0de15451098ffbf5497680c165d5e3e0e33d70.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5120/20888-3666"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Invariant Information Clustering for Unsupervised Image Classification and Segmentation [article]

Xu Ji, João F. Henriques, Andrea Vedaldi
<span title="2019-03-26">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The first achieves 88.8% accuracy on STL10 classification, setting a new global state-of-the-art over all existing methods (whether supervised, semi supervised or unsupervised).  ...  In addition to the fully unsupervised mode, we also test two semi-supervised settings.  ...  More generally, learning from paired data has also been explored in co-clustering [24] and in other works [47] that build on the information bottleneck principle [19] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.06653v3">arXiv:1807.06653v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f4u7gexfazcrjiwp7ascx5xylu">fatcat:f4u7gexfazcrjiwp7ascx5xylu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929233156/https://arxiv.org/pdf/1807.06653v3.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/0c/9a/0c9ae806059196007938f24d0327a4237ed6adf5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.06653v3" 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>

Word sense disambiguation using label propagation based semi-supervised learning

Zheng-Yu Niu, Dong-Hong Ji, Chew Lim Tan
<span title="">2005</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL &#39;05</a> </i> &nbsp;
Shortage of manually sense-tagged data is an obstacle to supervised word sense disambiguation methods.  ...  In this paper we investigate a label propagation based semisupervised learning algorithm for WSD, which combines labeled and unlabeled data in learning process to fully realize a global consistency assumption  ...  Niu is supported by A*STAR Graduate Scholarship.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/1219840.1219889">doi:10.3115/1219840.1219889</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/NiuJT05.html">dblp:conf/acl/NiuJT05</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6jypscqnjbd3dmyknwnqb5xvvy">fatcat:6jypscqnjbd3dmyknwnqb5xvvy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170813220836/http://www.aclweb.org/anthology/P/P05/P05-1049.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/64/f4/64f4a1a0a1fc0e4669e90f65c25e4a2e210a4958.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/1219840.1219889"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Review: Semi-Supervised Learning Methods for Word Sense Disambiguation

Ms. Ankita Sati
<span title="">2013</span> <i title="IOSR Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vabuspdninc75epczdurccts4u" style="color: black;">IOSR Journal of Computer Engineering</a> </i> &nbsp;
In this paper, we discuss the methods of semi-supervised learning and their performance.  ...  Word sense disambiguation (WSD) is an open problem of natural language processing, which governs the process of identifying the appropriate sense of a word in a sentence, when the word has multiple meanings  ...  Semi-Supervised Learning Techniques The semi-supervised or minimally supervised methods are gaining popularity because of their ability to get by with only a small amount of annotated reference data while  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.9790/0661-1246368">doi:10.9790/0661-1246368</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ygxtozhq5attf4xoakyomyfra">fatcat:2ygxtozhq5attf4xoakyomyfra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180602151620/http://www.iosrjournals.org/iosr-jce/papers/Vol12-issue4/K01246368.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/0d/bc0d94c489faf8edd2d6c730a3d62f57292fbf56.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.9790/0661-1246368"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Using Supervised Clustering to Enhance Classifiers [chapter]

Christoph F. Eick, Nidal Zeidat
<span title="">2005</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
This paper centers on a novel data mining technique we term supervised clustering.  ...  Unlike traditional clustering, supervised clustering is applied to classified examples and has the goal of identifying class-uniform clusters that have a high probability density.  ...  Similarly, Tishby et. al. introduce the information bottleneck method [9] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/11425274_26">doi:10.1007/11425274_26</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sbo67wj2hnhutfkb4xuw2iggn4">fatcat:sbo67wj2hnhutfkb4xuw2iggn4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20070412044843/http://www2.cs.uh.edu:80/~ceick/kdd/EZ05.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/ed/45/ed45dfc7d30b2b5de17be1eb9bff661dd8f4d6b1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/11425274_26"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Semi-supervised distance metric learning for collaborative image retrieval and clustering

Steven C.h. Hoi, Wei Liu, Shih-Fu Chang
<span title="2010-08-01">2010</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xdpft7x43zeqnbvjpgywfvawym" style="color: black;">ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)</a> </i> &nbsp;
In this article, we present a novel framework of Semi-Supervised Distance Metric Learning for learning effective distance metrics by exploring the historical relevance feedback log data of a CBIR system  ...  We conduct extensive evaluation to compare the proposed LRML method with a number of competing methods, including 2 standard metrics, 3 unsupervised metrics, and 4 supervised metrics with side information  ...  Section 3 formally defines the distance metric learning problem and proposes the framework of semi-supervised distance metric learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1823746.1823752">doi:10.1145/1823746.1823752</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jayuttfmmfbfhgtdohcgoygvgq">fatcat:jayuttfmmfbfhgtdohcgoygvgq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20110401071035/http://www.ee.columbia.edu/ln/dvmm/publications/10/TOMCCAP10_ssml.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/cf/5c/cf5c97cde2e2e95327add10ced56a4ffde9cac8c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1823746.1823752"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Dynamic β-VAEs for quantifying biodiversity by clustering optically recorded insect signals [article]

Klas Rydhmer, Raghavendra Selvan
<span title="2021-10-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also demonstrate improved clustering performance in a semi-supervised setting using a small subset of labelled data.  ...  In order to improve upon existing insect clustering methods, we propose an adaptive variant of the variational autoencoder (VAE) which is capable of clustering data by phylogenetic groups.  ...  Exploring the latent space Samples generated from the latent space of the semi-supervised model are shown as a latent space cart-wheel in Figure 5 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.05526v2">arXiv:2102.05526v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kqew55wi6feqnj4ampt5ppiz7q">fatcat:kqew55wi6feqnj4ampt5ppiz7q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211007025459/https://arxiv.org/pdf/2102.05526v2.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/18/bf/18bfc290cbfd1e6837a5dbe4a72140b3ff96bae3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.05526v2" 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>

LiDAM: Semi-Supervised Learning with Localized Domain Adaptation and Iterative Matching [article]

Qun Liu, Matthew Shreve, Raja Bala
<span title="2020-11-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Semi-supervised learning methods combine a few labeled samples with a large corpus of unlabeled data to effectively train models.  ...  This paper introduces our proposed method LiDAM, a semi-supervised learning approach rooted in both domain adaptation and self-paced learning.  ...  Semi-supervised learning While a comprehensive survey of the semi-supervised learning literature is beyond scope, here we highlight a few techniques related to our approach.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.06668v2">arXiv:2010.06668v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lahtd4eqqrbfjd3beahtcuqb2y">fatcat:lahtd4eqqrbfjd3beahtcuqb2y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201119004104/https://arxiv.org/pdf/2010.06668v1.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/2d/73/2d73699c09a791353f9d8217b8e0aedafe7bc0b8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.06668v2" 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 5,318 results