Filters








164 Hits in 7.9 sec

NAM: Non-Adversarial Unsupervised Domain Mapping [article]

Yedid Hoshen, Lior Wolf
<span title="2018-09-04">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we introduce an alternative method: Non-Adversarial Mapping (NAM), which separates the task of target domain generative modeling from the cross-domain mapping task.  ...  NAM relies on a pre-trained generative model of the target domain, and aligns each source image with an image synthesized from the target domain, while jointly optimizing the domain mapping function.  ...  Unsupervised Image Mapping without GANs In this section, we present our method -NAM -for unsupervised domain mapping. The task we aim to solve, is finding analogous images across domains.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.00804v2">arXiv:1806.00804v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/duhlmbcx2fcljjyjc5fbkdeq6q">fatcat:duhlmbcx2fcljjyjc5fbkdeq6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915090935/https://arxiv.org/pdf/1806.00804v2.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/3a/93/3a932415232bb54138d4b0e7a45aea936772c12e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.00804v2" 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>

NAM: Non-Adversarial Unsupervised Domain Mapping [chapter]

Yedid Hoshen, Lior Wolf
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
NAM relies on a pre-trained generative model of the target domain, and aligns each source image with an image synthesized from the target domain, while jointly optimizing the domain mapping function.  ...  In addition, most methods rely heavily on "cycle" relationships between the domains, which enforce a one-to-one mapping.  ...  Unsupervised Image Mapping without GANs In this section, we present our method -NAM -for unsupervised domain mapping. The task we aim to solve, is finding analogous images across domains.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01264-9_27">doi:10.1007/978-3-030-01264-9_27</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/br2lqynqdvfmznhyg6pfzcxgym">fatcat:br2lqynqdvfmznhyg6pfzcxgym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190714045333/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Yedid_Hoshen_Separable_Cross-Domain_Translation_ECCV_2018_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/bb/1b/bb1b3eb2647cb7971a23ccbdde0fbde4e3817915.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01264-9_27"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation [article]

Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gkhan Uzunbas, Tom Goldstein, Ser Nam Lim, Larry S. Davis
<span title="2018-04-16">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
and the segmentation network further refines high-level features before predicting semantic maps, both of which leverage feature statistics of sampled images from the target domain.  ...  In particular, given an image from the source domain and unlabeled samples from the target domain, the generator synthesizes new images on-the-fly to resemble samples from the target domain in appearance  ...  GANs have also been further extended to the problem of image-to-image translation, which maps a given image to another one in a different style, using cycle consistency [43] or a shared latent space  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.05827v1">arXiv:1804.05827v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jtjhx5levreb5e53wkt47yz2xm">fatcat:jtjhx5levreb5e53wkt47yz2xm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200918092617/https://arxiv.org/pdf/1804.05827v1.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/cd/30/cd30f2c60c31d6e12fadc49ef39818faf1843cba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.05827v1" 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>

DCAN: Dual Channel-Wise Alignment Networks for Unsupervised Scene Adaptation [chapter]

Zuxuan Wu, Xintong Han, Yen-Liang Lin, Mustafa Gökhan Uzunbas, Tom Goldstein, Ser Nam Lim, Larry S. Davis
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
and the segmentation network further refines highlevel features before predicting semantic maps, both of which leverage feature statistics of sampled images from the target domain.  ...  In particular, given an image from the source domain and unlabeled samples from the target domain, the generator synthesizes new images on-the-fly to resemble samples from the target domain in appearance  ...  Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01228-1_32">doi:10.1007/978-3-030-01228-1_32</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gdesitnfhjh7jatknwpypwav3m">fatcat:gdesitnfhjh7jatknwpypwav3m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200318082444/http://openaccess.thecvf.com/content_ECCV_2018/papers/Zuxuan_Wu_DCAN_Dual_Channel-wise_ECCV_2018_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/03/0f/030ff7012b92b805a60976f8dbd6a08c1cecebe6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01228-1_32"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Generating 3D texture models of vessel pipes using 2D texture transferred by object recognition☆

Min-Ji Kim, Kyung-Ho Lee, Young-Soo Han, Jaejoon Lee, Byungwook Nam
<span title="2021-01-09">2021</span> <i title="Oxford University Press (OUP)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wwsc42z63rfpzivxx6wex5t55i" style="color: black;">Journal of Computational Design and Engineering</a> </i> &nbsp;
These ships entail high production costs and long-life cycles.  ...  This problem is particularly evident when mapping various texture characteristics to virtual objects.  ...  The GAN structure, which uses unsupervised learning, consists of a generator and a discriminator.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/jcde/qwaa090">doi:10.1093/jcde/qwaa090</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/roiwxngwrnetvnz4bmg5sscnu4">fatcat:roiwxngwrnetvnz4bmg5sscnu4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210228002207/https://watermark.silverchair.com/qwaa090.pdf?token=AQECAHi208BE49Ooan9kkhW_Ercy7Dm3ZL_9Cf3qfKAc485ysgAAAp8wggKbBgkqhkiG9w0BBwagggKMMIICiAIBADCCAoEGCSqGSIb3DQEHATAeBglghkgBZQMEAS4wEQQMNmL5xF0xNN7LCecEAgEQgIICUvc_ryd6ju-bom0MHtNv1whqhMjGh_tu_Dk3sHdhus9YeFIfweArJIpf6TbBpiL_3qQ7hWnIajZes1QTuTTsN9ZoyjBtYnLebH7gEMjC8cHLJQx5T601PK_h6DFExM90tTNfO-4IhNVHBhHsOcC_M835wOWLee47S1NiNX2y0zvNvzW32fImTER-iFQxXmKskWPoTAF2ejUgKdHuSDAlOyyHt0KhPLu3OCEIyNekL18vUWgj0pjx6d4nqPpdrCuWh7BDIphUUTVg_xOFmNwfn5UO4cZpta_622B-wFRnkYlqGHmk67tPuXci2cpTxOpdFC5hQBPo5JEEEvuXhwPOKMg4qrKCL7Y4mKdf9jG-OaZurfd9nie7qONRRSnGhvIyfSW3sx1pbUAD8xCzmgRMkVvZLX6W6vwMHdB8R6toax-koTM2FELjxOfiJe7mnguh6--93o7-PCD9HbNEDfer8iQNqvOzhuKozHl6gMh7Y_Pu8rZG_i7ZIYx7r0c3iNSWD0C5jfTgPxVc10bwuKRNTx0MibAcAdrnCCvTeJ5e1XNT07v3lOJx25WsfmgDrDYVGzApqXOKw1CtJpy53_0GjoxDQS6ximBK-koApwrQ6Bwte6s9atkeTA68iJvy1VLYFY-aG-HL2V_KB_OhCDLpc80NdUob1_PHlgNQoxPwMLmJPzdXfzSmvTm-Vny72sjXyseZCMkFvODMqsqFepM6qXIqsYod50QnZV9Efgzg_sPvIXn3drjGjPnutrMb1jF6fVg5tOlxyxWUD5Ke0gKDVNy3Rg" 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/77/bc7764ff605831743b536424f59fc4cd81d38f82.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1093/jcde/qwaa090"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> oup.com </button> </a>

CrossNet: Latent Cross-Consistency for Unpaired Image Translation

Omry Sendik, Dani Lischinski, Daniel Cohen-Or
<span title="">2020</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2020 IEEE Winter Conference on Applications of Computer Vision (WACV)</a> </i> &nbsp;
In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing  ...  These cross-translators enable us to impose several regularizing constraints on the learnt image translation operator, collectively referred to as latent cross-consistency.  ...  One GAN maps images from domain A to domain B, and a second one operates in the opposite direction (from B to A).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv45572.2020.9093322">doi:10.1109/wacv45572.2020.9093322</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/SendikLC20.html">dblp:conf/wacv/SendikLC20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ehdntjb3v5e2xmwydg4kxaajzm">fatcat:ehdntjb3v5e2xmwydg4kxaajzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200709213841/https://openaccess.thecvf.com/content_WACV_2020/papers/Sendik_CrossNet_Latent_Cross-Consistency_for_Unpaired_Image_Translation_WACV_2020_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/c1/fc/c1fc83f6f7d310ab3ac44062b41bd400894fb0f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv45572.2020.9093322"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

CrossNet: Latent Cross-Consistency for Unpaired Image Translation [article]

Omry Sendik, Dani Lischinski, Daniel Cohen-Or
<span title="2019-05-26">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In particular, it was shown that a wide variety of image translation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing  ...  Recent GAN-based architectures have been able to deliver impressive performance on the general task of image-to-image translation.  ...  One GAN maps images from domain A to domain B, and a second one operates in the opposite direction (from B to A).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.04530v2">arXiv:1901.04530v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sq4zfvv3bnbg5aus66f35fdl44">fatcat:sq4zfvv3bnbg5aus66f35fdl44</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930105415/https://arxiv.org/pdf/1901.04530v1.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/c0/43/c0435f20ff52ba0a6fe902ff9d827bdd7f22f2a4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1901.04530v2" 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 for Future Wireless Networks: A Comprehensive Survey [article]

Cong T. Nguyen, Nguyen Van Huynh, Nam H. Chu, Yuris Mulya Saputra, Dinh Thai Hoang, Diep N. Nguyen, Quoc-Viet Pham, Dusit Niyato, Eryk Dutkiewicz, Won-Joo Hwang
<span title="2021-08-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
weekends), and cross-domain (BSs and their coordinates) datasets.  ...  The GAN-based TL approach [73] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.07572v2">arXiv:2102.07572v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/56si46duuvg55htquyhoawwg6m">fatcat:56si46duuvg55htquyhoawwg6m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210812053303/https://arxiv.org/pdf/2102.07572v2.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/97/9e/979ec8aed4e9d8ab3c125cf3d63cb021a6596be0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.07572v2" 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>

Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation

Bo Yuan, Danpei Zhao, Shuai Shao, Zehuan Yuan, Changhu Wang
<span title="2022-03-31">2022</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dhlhr4jqkbcmdbua2ca45o7kru" style="color: black;">IEEE Transactions on Image Processing</a> </i> &nbsp;
Based on our proposed methods, we also raise a hierarchical unsupervised domain adaptation framework for cross-domain semantic segmentation task.  ...  Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain.  ...  The GANbased methods have been widely used in image-level domain mapping.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2022.3162471">doi:10.1109/tip.2022.3162471</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35358045">pmid:35358045</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m6i7oxcqhbfy3iagceh4mn7e4i">fatcat:m6i7oxcqhbfy3iagceh4mn7e4i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220530044045/https://arxiv.org/pdf/2204.02111v1.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/0d/e2/0de229ba6c0ea523074dca5bfb86402a110ffcfd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tip.2022.3162471"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Domain Intersection and Domain Difference [article]

Sagie Benaim, Michael Khaitov, Tomer Galanti, Lior Wolf
<span title="2019-08-30">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This allows us to map from one domain to the other, in a way in which the content that is specific for the first domain is removed and the content that is specific for the second is imported from any image  ...  In addition, our method enables generation of images from the intersection of the two domains as well as their union, despite having no such samples during training.  ...  It does not employ GANs in the visual domains, or cycles of any sort.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.11628v1">arXiv:1908.11628v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xgnl4y3wyrccdihm6ka3dghmpe">fatcat:xgnl4y3wyrccdihm6ka3dghmpe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200929030710/https://arxiv.org/pdf/1908.11628v1.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/66/b7/66b7eab70cd66dfe1edb2220924856de377a6000.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.11628v1" 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 Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey [article]

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
<span title="2021-12-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
, domain generalization, test-time adaptation or source-free domain adaptation; we conclude this survey by describing datasets and benchmarks most widely used in semantic segmentation research.  ...  Since unlabelled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation reached a broad success within the semantic segmentation community.  ...  Toldo et al. [187] perform image-level domain adap- where GS→T and GT →S are the image generators that learn tation with Cycle-GAN  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.03241v1">arXiv:2112.03241v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uzlehddvuvfwzf4dfbjimja45e">fatcat:uzlehddvuvfwzf4dfbjimja45e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208153642/https://arxiv.org/pdf/2112.03241v1.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/ab/b7/abb79bf15896e0922427ca9d35b0e36ec6718e6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.03241v1" 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>

Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach [article]

Yahui Liu, Marco De Nadai, Deng Cai, Huayang Li, Xavier Alameda-Pineda, Nicu Sebe, Bruno Lepri
<span title="2020-08-10">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Previous research usually requires either the user to describe all the characteristics of the desired image or to use richly-annotated image captioning datasets.  ...  In this work, we propose a novel unsupervised approach, based on image-to-image translation, that alters the attributes of a given image through a command-like sentence such as "change the hair color to  ...  Image-to-image translation: Conditional GANs were first employed for image-to-image translation in pix2pix [21] for learning a mapping from one domain to another by minimizing the L 1 loss between the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.04200v1">arXiv:2008.04200v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/liyskz7lsfhnfl3b7fsyfethwa">fatcat:liyskz7lsfhnfl3b7fsyfethwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201014130716/https://arxiv.org/pdf/2008.04200v1.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/a1/3d/a13d21c301d3874baf1ca7a442649eb665ef5418.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.04200v1" 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>

New Ideas and Trends in Deep Multimodal Content Understanding: A Review [article]

Wei Chen and Weiping Wang and Li Liu and Michael S. Lew
<span title="2020-10-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
These models go beyond the simple image classifiers in which they can do uni-directional (e.g. image captioning, image generation) and bi-directional (e.g. cross-modal retrieval, visual question answering  ...  The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text.  ...  For example, in the first work about unsupervised image captioning [121] , the core idea of GANs is used to generate meaningful text features from scratch of text corpus and cross-reconstruction is performed  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08189v1">arXiv:2010.08189v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2l7molbcn5hf3oyhe3l52tdwra">fatcat:2l7molbcn5hf3oyhe3l52tdwra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201023005952/https://arxiv.org/pdf/2010.08189v1.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/61/ba/61ba6969078b7358c61f7eb93b4150ab0e4f329b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08189v1" 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 Domain Adaptation in Speech Recognition using Phonetic Features [article]

Rupam Ojha, C Chandra Sekhar
<span title="2021-08-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a technique to perform unsupervised gender-based domain adaptation in speech recognition using phonetic features.  ...  As a result, domain adaptation is important in speech recognition where we train the model for a particular source domain and test it on a different target domain.  ...  Approaches to explore the gender based domain adaptation for speech recognition include cycle-GAN [7] , multi-discriminator cycle-GAN [8] and augmented cycle adversarial learning [9] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.02850v1">arXiv:2108.02850v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mp4prfyp4repvbjtaf2qwy7qmu">fatcat:mp4prfyp4repvbjtaf2qwy7qmu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210811102322/https://arxiv.org/pdf/2108.02850v1.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/2e/d6/2ed61636758af9dc3cbe1fa157eb835462bcb594.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.02850v1" 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 of Image Information Hiding Algorithms Based on Deep Learning

Ruohan Meng, Qi Cui, Chengsheng Yuan
<span title="2018-12-29">2018</span> <i title="Computers, Materials and Continua (Tech Science Press)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5affhnnafnhcngr6wusyti3yru" style="color: black;">CMES - Computer Modeling in Engineering &amp; Sciences</a> </i> &nbsp;
Ensuring that the stego image cannot be distinguished from the cover image, and sending secret information to receiver through the transmission of the stego image.  ...  Image information hiding is to make use of the redundancy of the cover image to hide secret information in it.  ...  In the field of unsupervised learning, GAN is a typical representative. The basic principle of GAN is that it has two models: A generator and a discriminator.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.31614/cmes.2018.04765">doi:10.31614/cmes.2018.04765</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tvmits2gdrb4xesfswtr275wpy">fatcat:tvmits2gdrb4xesfswtr275wpy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430235033/http://tsp.techscience.com//uploads/attached/file/20181229/20181229072639_56988.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/e9/53/e953ebb0d4637044c90436de5b973d64b3f45dcc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.31614/cmes.2018.04765"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 164 results