Filters








21,030 Hits in 7.5 sec

Generate To Adapt: Aligning Domains using Generative Adversarial Networks [article]

Swami Sankaranarayanan, Yogesh Balaji, Carlos D. Castillo, Rama Chellappa
2018 arXiv   pre-print
(2) Object recognition using OFFICE dataset and (3) Domain adaptation from synthetic to real data.  ...  This is in contrast to methods which use the adversarial framework for realistic data generation and retraining deep models with such data.  ...  [31] and [1] use adversarial networks to map source images to target and perform adaptation in the transferred space.  ... 
arXiv:1704.01705v4 fatcat:qmaiwj277zahhbenkyyrs2lwoi

Generate to Adapt: Aligning Domains Using Generative Adversarial Networks

Swami Sankaranarayanan, Yogesh Balaji, Carlos D. Castillo, Rama Chellappa
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
(2) Object recognition using OFFICE dataset and (3) Domain adaptation from synthetic to real data.  ...  This is in contrast to methods which use the adversarial framework for realistic data generation and retraining deep models with such data.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
doi:10.1109/cvpr.2018.00887 dblp:conf/cvpr/Sankaranarayanan18a fatcat:y3ueuaswxjbrdhbxgsz2kacbqu

Synthetic to Real Adaptation with Generative Correlation Alignment Networks [article]

Xingchao Peng, Kate Saenko
2017 arXiv   pre-print
In this work, we propose a Deep Generative Correlation Alignment Network (DGCAN) to synthesize images using a novel domain adaption algorithm.  ...  Recent work has shown the great potential of deep convolutional neural networks to generate realistic images, but has not utilized generative models to address synthetic-to-real domain adaptation.  ...  Deep domain adaptation methods address the domain shift by adding one or multiple adaptation layers and losses [41, 40, 20, 38] , or use an adversarial network to match the source distribution to target  ... 
arXiv:1701.05524v3 fatcat:mvzexxnr4jaarpwdzbudquj3im

Generative Adversarial Networks for Video-to-Video Domain Adaptation [article]

Jiawei Chen, Yuexiang Li, Kai Ma, Yefeng Zheng
2020 arXiv   pre-print
In this work, we propose a novel generative adversarial network (GAN), namely VideoGAN, to transfer the video-based data across different domains.  ...  ., color and illumination, which make the models trained on one domain usually fail to generalize well to another. Domain adaptation is one of the potential solutions to address the problem.  ...  In this paper, we propose a novel generative adversarial network, namely VideoGAN, for domain adaptation of multicentre endoscopic videos.  ... 
arXiv:2004.08058v1 fatcat:72bmzh6zujadnpltdksawg27i4

Generative Adversarial Networks for Video-to-Video Domain Adaptation

Jiawei Chen, Yuexiang Li, Kai Ma, Yefeng Zheng
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this work, we propose a novel generative adversarial network (GAN), namely VideoGAN, to transfer the video-based data across different domains.  ...  ., color and illumination, which make the models trained on one domain usually fail to generalize well to another. Domain adaptation is one of the potential solutions to address the problem.  ...  In this paper, we propose a novel generative adversarial network, namely VideoGAN, for domain adaptation of multicentre endoscopic videos.  ... 
doi:10.1609/aaai.v34i04.5750 fatcat:w6ywcjpzhjdfvjeny6jlspoacq

Learning to Zoom-in via Learning to Zoom-out: Real-world Super-resolution by Generating and Adapting Degradation [article]

Dong Gong, Wei Sun, Qinfeng Shi, Anton van den Hengel, Yanning Zhang
2020 arXiv   pre-print
Instead of assuming the domain gap has been eliminated, we minimize the discrepancy between the generated data and real data while learning a degradation adaptive SR network (i.e., learning to zoom in)  ...  To do so, we firstly train a degradation generation network to generate realistic LR images and, more importantly, to capture their distribution (i.e., learning to zoom out).  ...  We propose an adaptive loss to align the network responses of I L gen and I L real , which is designed as a adversarial loss between the features of I L gen and I L real : L ada ( R, D ada ) = E I L gen  ... 
arXiv:2001.02381v1 fatcat:bxy4me2mirhkpa4azrczliaflq

Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection [article]

Christian Abbet, Linda Studer, Andreas Fischer, Heather Dawson, Inti Zlobec, Behzad Bozorgtabar, Jean-Philippe Thiran
2022 arXiv   pre-print
Making use of open-source data for pre-training or using domain adaptation can be a way to overcome this issue.  ...  However, pre-trained networks often fail to generalize to new test domains that are not distributed identically due to tissue stainings, types, and textures variations.  ...  The authors would like to thank Dr. Felix Müller, M. Med.  ... 
arXiv:2108.09178v2 fatcat:nhoqz2gx4rbwlbcjzcfcpfevga

A General Approach to Domain Adaptation with Applications in Astronomy [article]

Ricardo Vilalta, Kinjal Dhar Gupta, Dainis Boumber, Mikhail M. Meskhi
2018 arXiv   pre-print
In this paper we propose a new general approach to domain adaptation that does not rely on the proximity of source and target distributions.  ...  The problem is generally known as transfer learning in machine learning, where domain adaptation is a popular scenario.  ...  Domain-Adversarial Training of Neural Networks (DATNN) [57] .  ... 
arXiv:1812.08839v1 fatcat:vg4z7svc7vgihnwytjjy6my2im

U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation [article]

Junho Kim, Minjae Kim, Hyeonwoo Kang, Kwanghee Lee
2020 arXiv   pre-print
Experimental results show the superiority of the proposed method compared to the existing state-of-the-art models with a fixed network architecture and hyper-parameters.  ...  Moreover, our new AdaLIN (Adaptive Layer-Instance Normalization) function helps our attention-guided model to flexibly control the amount of change in shape and texture by learned parameters depending  ...  UNSUPERVISED GENERATIVE ATTENTIONAL NETWORKS WITH ADAPTIVE LAYER-INSTANCE NORMALIZATION Our goal is to train a function G s→t that maps images from a source domain X s to a target domain X t using only  ... 
arXiv:1907.10830v4 fatcat:u4bey3rm4zh27cyl6zmljgrfwu

Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control [article]

Lukas Hermann, Max Argus, Andreas Eitel, Artemij Amiranashvili, Wolfram Burgard, Thomas Brox
2020 arXiv   pre-print
parameters to use.  ...  We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards.  ...  A more evolved approach generates a curriculum of goals using a Generative Adversarial Network (GAN) but cannot handle visual goals [11] .  ... 
arXiv:1910.07972v3 fatcat:dexm2xv3jzfn7ihrqkyixkeb2u

Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation [article]

Dongchan Min, Dong Bok Lee, Eunho Yang, Sung Ju Hwang
2021 arXiv   pre-print
Specifically, we propose Style-Adaptive Layer Normalization (SALN) which aligns gain and bias of the text input according to the style extracted from a reference speech audio.  ...  With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications.  ...  We sincerely thank the anonymous reviewers for their constructive comments which helped us significantly improve our paper during the rebuttal period.  ... 
arXiv:2106.03153v3 fatcat:fqlq3xyt5fbalbjvli4eq7gfk4

Generalizing to Unseen Domains: A Survey on Domain Generalization [article]

Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, Philip S. Yu
2022 arXiv   pre-print
Domain generalization deals with a challenging setting where one or several different but related domain(s) are given, and the goal is to learn a model that can generalize to an unseen test domain.  ...  We then thoroughly review the theories related to domain generalization and carefully analyze the theory behind generalization.  ...  [92] proposed Domain-adversarial neural network (DANN) for domain adaptation, which adversarially trains the generator and discriminator.  ... 
arXiv:2103.03097v7 fatcat:ry4ggjl63bhlzdhg3gojvyk2v4

Self-adaptive Re-weighted Adversarial Domain Adaptation [article]

Shanshan Wang, Lei Zhang
2020 arXiv   pre-print
To address this problem, we present a self-adaptive re-weighted adversarial domain adaptation approach, which tries to enhance domain alignment from the perspective of conditional distribution.  ...  Existing adversarial domain adaptation methods mainly consider the marginal distribution and these methods may lead to either under transfer or negative transfer.  ...  Our method aims to construct a target generalized network. The re-weighted adversarial domain adaptation forces a close global domain-level alignment.  ... 
arXiv:2006.00223v2 fatcat:nsreyyy32jakljejrerlatfyya

Generic Indic Text-to-speech Synthesisers with Rapid Adaptation in an End-to-end Framework [article]

Anusha Prakash, Hema A Murthy
2020 arXiv   pre-print
These systems are then adapted to a new language in the same family using small amounts of adaptation data.  ...  The proposed work exploits this property to build a generic TTS system using multiple languages from the same family in an end-to-end framework.  ...  The authors would like to thank the Ministry of Electronics and Information Technology (MeitY), Government of India, for funding the project, "Text to Speech Generation with chosen accent and noise profile  ... 
arXiv:2006.06971v1 fatcat:uhxwuf5vw5c37lm3iogbgteljq

Learning to Generate Novel Domains for Domain Generalization [article]

Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang
2021 arXiv   pre-print
To train the generator, we model the distribution divergence between source and synthesized pseudo-novel domains using optimal transport, and maximize the divergence.  ...  This paper focuses on domain generalization (DG), the task of learning from multiple source domains a model that generalizes well to unseen domains.  ...  generator network.  ... 
arXiv:2007.03304v3 fatcat:esfi3fkksngxbfjbbzwu6lqkqi
« Previous Showing results 1 — 15 out of 21,030 results