Filters








1,253 Hits in 4.5 sec

Unsupervised Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks [article]

Minjun Li, Haozhi Huang, Lin Ma, Wei Liu, Tong Zhang, Yu-Gang Jiang
<span title="2018-07-28">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss.  ...  In this paper, we propose novel Stacked Cycle-Consistent Adversarial Networks (SCANs) by decomposing a single translation into multi-stage transformations, which not only boost the image translation quality  ...  In this paper, we propose the stacked cycle-consistent adversarial networks (SCANs) aiming for unsupervised learning of image-to-image translation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.08536v2">arXiv:1807.08536v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lt3kdoyvsng7jdp36cjj7c3plq">fatcat:lt3kdoyvsng7jdp36cjj7c3plq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191015061732/https://arxiv.org/pdf/1807.08536v2.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/a7/0a/a70afd0a538168c58e933784067b0d18a94bf785.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.08536v2" 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 Image-to-Image Translation with Stacked Cycle-Consistent Adversarial Networks [chapter]

Minjun Li, Haozhi Huang, Lin Ma, Wei Liu, Tong Zhang, Yugang Jiang
<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;
Recent studies on unsupervised image-to-image translation have made remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss.  ...  In this paper, we propose novel Stacked Cycle-Consistent Adversarial Networks (SCANs) by decomposing a single translation into multi-stage transformations, which not only boost the image translation quality  ...  In this paper, we propose the stacked cycle-consistent adversarial networks (SCANs) for the unsupervised learning of image-to-image translation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01240-3_12">doi:10.1007/978-3-030-01240-3_12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mxwsmymx45hgzc7sqrbvxnw6yy">fatcat:mxwsmymx45hgzc7sqrbvxnw6yy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190714223416/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Minjun_Li_Unsupervised_Image-to-Image_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/6e/ca/6ecaa7ca16f4ef650670b13ade18ccf62fa98a6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01240-3_12"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Dual Contrastive Learning for Unsupervised Image-to-Image Translation [article]

Junlin Han, Mehrdad Shoeiby, Lars Petersson, Mohammad Ali Armin
<span title="2021-04-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised image-to-image translation tasks aim to find a mapping between a source domain X and a target domain Y from unpaired training data.  ...  Contrastive learning for Unpaired image-to-image Translation (CUT) yields state-of-the-art results in modeling unsupervised image-to-image translation by maximizing mutual information between input and  ...  Unpaired image-to-image translation using cycle- [33] Ori Nizan and Ayellet Tal. Breaking the cycle - colleagues consistent adversarial networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.07689v1">arXiv:2104.07689v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xd5xi5rqrfbjnm4qqbl75yq6ge">fatcat:xd5xi5rqrfbjnm4qqbl75yq6ge</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210831130537/https://arxiv.org/pdf/2104.07689v1.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/42/cd423b798967c42f9efc7aa5efe09917a5c37fd3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.07689v1" 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 Shadow Removal Using Target Consistency Generative Adversarial Network [article]

Chao Tan, Xin Feng
<span title="2021-05-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Compared with the bidirectional mapping in cycle-consistency GAN based methods for shadow removal, TC-GAN tries to learn a one-sided mapping to cast shadow images into shadow-free ones.  ...  In this paper, we develop a simple yet efficient target-consistency generative adversarial network (TC-GAN) for the shadow removal task in the unsupervised manner.  ...  [49] develop a geometry-consistent generative adversarial network to perform one-sided unsupervised image-to-image translation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01291v2">arXiv:2010.01291v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/de5sx6mgnbarhgg736b625m2mu">fatcat:de5sx6mgnbarhgg736b625m2mu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201007003434/https://arxiv.org/ftp/arxiv/papers/2010/2010.01291.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> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01291v2" 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 Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks [article]

Yuan Yuan, Siyuan Liu, Jiawei Zhang, Yongbing Zhang, Chao Dong, and Liang Lin
<span title="2018-09-03">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With generative adversarial networks (GAN) as the basic component, we propose a Cycle-in-Cycle network structure to tackle the problem within three steps.  ...  To solve this problem, we resort to unsupervised learning without paired data, inspired by the recent successful image-to-image translation applications.  ...  For simplicity, we directly adopt EDSR as the SR network stacked after G 1 . Similarly, we use a discriminator D 2 for adversarial training both G 1 and SR networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.00437v1">arXiv:1809.00437v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/27vu4hb6wffddcvvftwl77grxa">fatcat:27vu4hb6wffddcvvftwl77grxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830064414/https://arxiv.org/pdf/1809.00437v1.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/d9/ed/d9ed2baf33fd21addd8e68df7c9b5d01cfef09f9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1809.00437v1" 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>

Adversarial Uni- and Multi-modal Stream Networks for Multimodal Image Registration [article]

Zhe Xu, Jie Luo, Jiangpeng Yan, Ritvik Pulya, Xiu Li, William Wells III, Jayender Jagadeesan
<span title="2020-09-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a novel translation-based unsupervised deformable image registration method.  ...  Distinct from other translation-based methods that attempt to convert the multimodal problem (e.g., CT-to-MR) into a unimodal problem (e.g., MR-to-MR) via image-to-image translation, our method leverages  ...  Image-to-Image Translation with Unpaired Data The CT-to-MR translation step consists of an improved Cycle-GAN with additional structural and identical constraints.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.02790v2">arXiv:2007.02790v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wg2smzc7szdelpdd3spxmjgbia">fatcat:wg2smzc7szdelpdd3spxmjgbia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200923001955/https://arxiv.org/pdf/2007.02790v2.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/2007.02790v2" 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>

TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translation

Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ilwxppn4d5hizekyd3ndvy2mii" style="color: black;">2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)</a> </i> &nbsp;
Abstract Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with failure.  ...  Figure 1 : We propose a geometry-aware framework for unsupervised image-to-image translation, which is robust to arbitrary shape variations between domains.  ...  We would like to thank Kwan-Yee Lin and Jingtan Piao for insightful discussion and their exceptional support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00820">doi:10.1109/cvpr.2019.00820</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cvpr/WuC00L19.html">dblp:conf/cvpr/WuC00L19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3sizpdozavaa3ll64lfjf2vbdy">fatcat:3sizpdozavaa3ll64lfjf2vbdy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190707151926/http://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_TransGaGa_Geometry-Aware_Unsupervised_Image-To-Image_Translation_CVPR_2019_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ad/05/ad05995d61244c40d25505cbfc85df156f1f35d4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cvpr.2019.00820"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation [article]

Wayne Wu, Kaidi Cao, Cheng Li, Chen Qian, Chen Change Loy
<span title="2019-04-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations always ends up with failure.  ...  In this work, we present a novel disentangle-and-translate framework to tackle the complex objects image-to-image translation task.  ...  We would like to thank Kwan-Yee Lin and Jingtan Piao for insightful discussion and their exceptional support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.09571v1">arXiv:1904.09571v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ilaie4eva5bwxpbyubpjgb2qbu">fatcat:ilaie4eva5bwxpbyubpjgb2qbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907043514/https://arxiv.org/pdf/1904.09571v1.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/d0/57/d05735fa4cf7b6bb4bb07cb7b2126971088310e4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.09571v1" 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 Image-to-Image Translation Networks [article]

Ming-Yu Liu and Thomas Breuel and Jan Kautz
<span title="2018-07-23">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We compare the proposed framework with competing approaches and present high quality image translation results on various challenging unsupervised image translation tasks, including street scene image  ...  To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs.  ...  In [25] , a conditional generative adversarial network-based approach was proposed to translate a rendering images to a real image for gaze estimation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.00848v6">arXiv:1703.00848v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e5ixr7aeszdi5avxout5rtsibm">fatcat:e5ixr7aeszdi5avxout5rtsibm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914075700/https://arxiv.org/pdf/1703.00848v6.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/7d/e5/7de59442e1979e424b0fa3f4c02344fb5932ef93.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1703.00848v6" 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 Invariant Representation for Unsupervised Image Restoration [article]

Wenchao Du, Hu Chen, Hongyu Yang
<span title="2020-03-28">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.  ...  consistency constraints, learning robust representation under dual domain constraints, such as feature and image domains.  ...  To enforce this constraint, we add the cross-cycle consistency loss L CC for X and Y domains: Adversarial Domain Adaption.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.12769v1">arXiv:2003.12769v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rdjmgqc2rrgtxo62f34ioft2lq">fatcat:rdjmgqc2rrgtxo62f34ioft2lq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200407054821/https://arxiv.org/pdf/2003.12769v1.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/2003.12769v1" 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>

H-GAN: the power of GANs in your Hands [article]

Sergiu Oprea, Giorgos Karvounas, Pablo Martinez-Gonzalez, Nikolaos Kyriazis, Sergio Orts-Escolano, Iason Oikonomidis, Alberto Garcia-Garcia, Aggeliki Tsoli, Jose Garcia-Rodriguez, Antonis Argyros
<span title="2021-04-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present HandGAN (H-GAN), a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators.  ...  It is designed to translate synthetic images of hands to the real domain.  ...  [10] proposed an attribute-conditioned Cycle-consistent Generative Adversarial Network (CycleGAN) generating multiple target images with different attributes e.g. day or night.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.15017v2">arXiv:2103.15017v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vfsuxdz6fzdltpgmmy4ucq373u">fatcat:vfsuxdz6fzdltpgmmy4ucq373u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210331042037/https://arxiv.org/pdf/2103.15017v1.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/3c/ef/3cef92845ee9a3ca890d3010121accd725f633c9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.15017v2" 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>

Semantics-Aware Image to Image Translation and Domain Transfer [article]

Pravakar Roy, Nicolai Häni, Volkan Isler
<span title="2019-04-03">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Image to image translation is the problem of transferring an image from a source domain to a target domain.  ...  Specifically, we present a Generative Adversarial Network (GAN) that can transfer semantic information presented as segmentation masks.  ...  Limitations and Discussion In this work, we presented an unsupervised image to image translation network which can transfer semantic labels consistently.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02203v1">arXiv:1904.02203v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5i4vtoamo5ahphjyaf5ipqmjzq">fatcat:5i4vtoamo5ahphjyaf5ipqmjzq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200915070202/https://arxiv.org/pdf/1904.02203v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/16/ab/16ab683a785bc30190935ce4f2f6e53d14020a40.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02203v1" 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>

DC2Anet: Generating Lumbar Spine MR Images from CT Scan Data Based on Semi-Supervised Learning

Cheng-Bin Jin, Hakil Kim, Mingjie Liu, In Ho Han, Jae Il Lee, Jung Hwan Lee, Seongsu Joo, Eunsik Park, Young Saem Ahn, Xuenan Cui
<span title="2019-06-20">2019</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
In this paper, we propose a method for estimating lumbar spine MR images based on CT images using a novel objective function and a dual cycle-consistent adversarial network (DC 2 Anet) with semi-supervised  ...  DC 2 Anet is also capable of semi-supervised learning, and the network is general enough for supervised or unsupervised setups.  ...  DC 2 Anet consists of a forward cycle-consistent and a backward cycle-consistent network. (a) The forward cycle-consistent adversarial network with unaligned learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app9122521">doi:10.3390/app9122521</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a3syg3ey5nfw3gf3kx4qaicatq">fatcat:a3syg3ey5nfw3gf3kx4qaicatq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200212133514/https://res.mdpi.com/d_attachment/applsci/applsci-09-02521/article_deploy/applsci-09-02521.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/9b/f3/9bf34e4b4bd1646c4529d0a8665bfb2498dbb430.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app9122521"> <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>

Attention-GAN for Object Transfiguration in Wild Images [article]

Xinyuan Chen, Chang Xu, Xiaokang Yang, Dacheng Tao
<span title="2018-03-19">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The attention network predicts spatial attention maps of images, and the transformation network focuses on translating objects.  ...  In contrast, we decompose the generative network into two separat networks, each of which is only dedicated to one particular sub-task.  ...  In image-to-image translation problem such as sketch to photo, map to aerial photo, day to night etc. [2] investigates conditional adversarial networks for a general solution.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.06798v1">arXiv:1803.06798v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7gkkngmr2fg2jpaqzhiazmnj2e">fatcat:7gkkngmr2fg2jpaqzhiazmnj2e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901092138/https://arxiv.org/pdf/1803.06798v1.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/f9/e5/f9e524e8be549375d4d4606b992b06ecd8c0ae1b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.06798v1" 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>

Generative Adversarial Networks for Video-to-Video Domain Adaptation

Jiawei Chen, Yuexiang Li, Kai Ma, Yefeng Zheng
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
As our VideoGAN is a general network architecture, we also evaluate its performance with the CamVid driving video dataset on the cloudy-to-sunny translation task.  ...  As the frames of a video may have similar content and imaging conditions, the proposed VideoGAN has an X-shape generator to preserve the intra-video consistency during translation.  ...  Unsupervised domain adaptation Apart from image-to-image translation, another area related to our work is the unsupervised domain adaptation (UDA).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i04.5750">doi:10.1609/aaai.v34i04.5750</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w6ywcjpzhjdfvjeny6jlspoacq">fatcat:w6ywcjpzhjdfvjeny6jlspoacq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103174006/https://aaai.org/ojs/index.php/AAAI/article/download/5750/5606" 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/ba/f1bacd43bbffc490914c3f11e82040f58a8a003d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i04.5750"> <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 1,253 results