93,714 Hits in 8.7 sec

Cross-Domain Visual Matching via Generalized Similarity Measure and Feature Learning

Liang Lin, Guangrun Wang, Wangmeng Zuo, Xiangchu Feng, Lei Zhang
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Moreover, we unify our similarity measure with feature representation learning via deep convolutional neural networks.  ...  Cross-domain visual data matching is one of the fundamental problems in many real-world vision tasks, e.g., matching persons across ID photos and surveillance videos.  ...  In summary, our similarity model can be regarded as the generalization of many existing cross-domain matching and metric learning models, and it is more flexible and suitable for cross-domain visual data  ... 
doi:10.1109/tpami.2016.2567386 pmid:27187945 fatcat:oxz5lfiquzdltnu4jhjefp5nru

Cross-Domain 3D Model Retrieval via Visual Domain Adaption

Anan Liu, Shu Xiang, Wenhui Li, Weizhi Nie, Yuting Su
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Consequently, it can augment the discrimination of visual descriptors for cross-domain similarity measure.  ...  This method can inherit the advantage of deep learning to learn multi-view visual features in the data-driven manner for 3D model representation.  ...  The output of CNN2 is fed into the module of cross-domain distance learning for feature projection and similarity measure.  ... 
doi:10.24963/ijcai.2018/115 dblp:conf/ijcai/LiuXLNS18 fatcat:pnraw22rezbu7dsgvpsi6fzmui

Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels [article]

Donghyun Kim, Kuniaki Saito, Tae-Hyun Oh, Bryan A. Plummer, Stan Sclaroff, Kate Saenko
2020 arXiv   pre-print
Our self-supervised learning method captures apparent visual similarity with in-domain self-supervision in a domain adaptive manner and performs cross-domain feature matching with across-domain self-supervision  ...  We propose a novel Cross-Domain Self-supervised (CDS) learning approach for domain adaptation, which learns features that are not only domain-invariant but also class-discriminative.  ...  In the across-domain self-supervision, we measure similarity between a feature and cross-domain features from the cross-domain memory bank and then minimize the entropy for cross-domain matching (best  ... 
arXiv:2003.08264v1 fatcat:75nlwwt3hvgtxfkvnwcqifqdea

Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization [article]

Li Ren, Kai Li, LiQiang Wang, Kien Hua
2020 arXiv   pre-print
The objective is to find efficient similarity metrics to compare the similarity between visual and textual information.  ...  Our approach can generally improve the learning efficiency and the performance of existing metrics learning frameworks by regulating the distribution of the hidden space between the matching pairs.  ...  Cross-Modal Matching with Domain Adaptation In this paper, we consider to train the feature generator g θ (·) by solving an unsupervised domain adaptation problem, which aims to generate the features with  ... 
arXiv:2010.12126v2 fatcat:we74xd3jdzdzlev2fewj7spf7m

Weakly supervised cross-domain alignment with optimal transport [article]

Siyang Yuan, Ke Bai, Liqun Chen, Yizhe Zhang, Chenyang Tao, Chunyuan Li, Guoyin Wang, Ricardo Henao, Lawrence Carin
2020 arXiv   pre-print
Cross-domain alignment between image objects and text sequences is key to many visual-language tasks, and it poses a fundamental challenge to both computer vision and natural language processing.  ...  Our method builds upon recent advances in optimal transport (OT) to resolve the cross-domain matching problem in a principled manner.  ...  The research at Duke University was supported in part by DARPA, DOE, NIH, NSF and ONR.  ... 
arXiv:2008.06597v1 fatcat:swzix2esmncstffyuyxjr2dbwq

Cross-Dataset Adaptation for Visual Question Answering

Fei Sha, Hexiang Hu, Wei-Lun Chao
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Analogous to domain adaptation for visual recognition, this setting is appealing when the target dataset does not have a sufficient amount of labeled data to learn an "in-domain" model.  ...  We investigate the problem of cross-dataset adaptation for visual question answering (Visual QA). Our goal is to train a Visual QA model on a source dataset but apply it to another target one.  ...  On the other hand, adding T to [Q], or vice versa, helps constructing a better measure to match the feature distribution between domains.  ... 
doi:10.1109/cvpr.2018.00599 dblp:conf/cvpr/ChaoHS18 fatcat:dleg5tpld5f3xdvhyejvu6bb2a

Generalising Fine-Grained Sketch-Based Image Retrieval

Kaiyue Pang, Ke Li, Yongxin Yang, Honggang Zhang, Timothy M. Hospedales, Tao Xiang, Yi-Zhe Song
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we identify cross-category generalisation for FG-SBIR as a domain generalisation problem, and propose the first solution.  ...  Our key contribution is a novel unsupervised learning approach to model a universal manifold of prototypical visual sketch traits.  ...  This work was supported in part by National Science Foundation of China (NSFC) under joint grant # 61701032 and # 61806184.  ... 
doi:10.1109/cvpr.2019.00077 dblp:conf/cvpr/Pang0YZHXS19 fatcat:spxubnmvpzam5oaitoiiqrnbze

Deep visual unsupervised domain adaptation for classification tasks: a survey

Yeganeh Madadi, Vahid Seydi, Kamal Nasrollahi, Reshad Hosseini, Thomas B. Moeslund
2020 IET Image Processing  
Learning methods are challenged when there is not enough labelled data. It gets worse when the existing learning data have different distributions in different domains.  ...  The survey includes the very recent papers on this topic that have not been included in the previous surveys and introduces a taxonomy by grouping methods published on unsupervised domain adaptation into  ...  [44] used GANs to transfer information from the source domain to the pixel-level target domain. They measured a pixel-level similarity via the colour version of structural similarity.  ... 
doi:10.1049/iet-ipr.2020.0087 fatcat:x7v5et3r6nagpe2ivuu5nd4qku

Connecting the dots without clues: Unsupervised domain adaptation for cross-domain visual classification

Wei-Yu Chen, Tzu-Ming Harry Hsu, Cheng-An Hou, Yi-Ren Yeh, Yu-Chiang Frank Wang
2015 2015 IEEE International Conference on Image Processing (ICIP)  
In this paper, we propose to exploit the cross-domain data correspondence using both observed data similarity and labels transferred from the source domain.  ...  This allows us to perform distribution matching for cross-domain data with recognition guarantees.  ...  Acknowledgement This work is supported in part by the Ministry of Science and Technology of Taiwan via MOST103-2221-E-001-021-MY2.  ... 
doi:10.1109/icip.2015.7351556 dblp:conf/icip/ChenHHYW15 fatcat:olds32fmcbea5pbji7n546qqbq

Construction of a Soundscape-Based Media Art Exhibition to Improve User Appreciation Experience by Using Deep Neural Networks

Youngjun Kim, Hayoung Jeong, Jun-Dong Cho, Jitae Shin
2021 Electronics  
The objective of this study was to improve user experience when appreciating visual artworks with soundscape music chosen by a deep neural network based on weakly supervised learning.  ...  Moreover, the concordance of implicit senses between artworks and classical music was measured to be 0.88%, and the time distortion and cognitive absorption improved during the immersion.  ...  This learning framework is similar to that of the soundnet framework; however, the pre-trained model with features shared via a multi-domain CNN, audio feature extraction via multi-time-scale transform  ... 
doi:10.3390/electronics10101170 fatcat:euyp6wqp6rblnmwfegbsbfmc7i

Cross-Domain Image Retrieval with Attention Modeling

Xin Ji, Wei Wang, Meihui Zhang, Yang Yang
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
With the proliferation of e-commerce websites and the ubiquitousness of smart phones, cross-domain image retrieval using images taken by smart phones as queries to search products on e-commerce websites  ...  Novel deep convolutional neural network architectures, namely TagYNet and CtxYNet, are proposed to learn the attention weights and then extract effective representations of the images.  ...  This design is to learn domain-invariant features by I and learn domain-specific features by subnetwork II and III.  ... 
doi:10.1145/3123266.3123429 dblp:conf/mm/JiWZY17 fatcat:kcovbxouwjfepdj5fpk66nv7qm

i3dLoc: Image-to-range Cross-domain Localization Robust to Inconsistent Environmental Conditions [article]

Peng Yin, Lingyun Xu, Ji Zhang, Howie Choset, Sebastian Scherer
2021 arXiv   pre-print
Our method can match equirectangular images to the 3D range projections by extracting cross-domain symmetric place descriptors.  ...  The problem is challenging because correspondences of local invariant features are inconsistent across the domains between image and 3D.  ...  Cross-domain Transfer Learning To generate constant geometry features from visual inputs under different environmental conditions, we construct a cross domain transfer network between 2D imagery and 3D  ... 
arXiv:2105.12883v2 fatcat:4epqm4vfq5efhle4kdg5lterrm

Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders [article]

Edgar Schönfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata
2019 arXiv   pre-print
Many approaches in generalized zero-shot learning rely on cross-modal mapping between the image feature space and the class embedding space.  ...  We evaluate our learned latent features on several benchmark datasets, i.e. CUB, SUN, AWA1 and AWA2, and establish a new state of the art on generalized zero-shot as well as on few-shot learning.  ...  In [25] a cross-aligned VAE ensures that the latent representations of texts from different input domains are similar, while in [16] a comparable approach matches the latent representations of images  ... 
arXiv:1812.01784v4 fatcat:px7zvsnsz5a5zfxt7vbvhxnh54

Web Multimedia Object Classification Using Cross-Domain Correlation Knowledge

Wenting Lu, Jingxuan Li, Tao Li, Weidong Guo, Honggang Zhang, Jun Guo
2013 IEEE transactions on multimedia  
Empirical experiments on two different datasets of web multimedia objects are conducted to demonstrate the efficacy and effectiveness of our proposed cross-domain transfer learning method.  ...  Given a collection of web images with the corresponding textual descriptions, in this paper, we propose a novel cross-domain learning method to classify these web multimedia objects by transferring the  ...  CROSS-DOMAIN TRANSFER LEARNING A. Framework Overview B.  ... 
doi:10.1109/tmm.2013.2280895 fatcat:ppgs7kapebby3b5vsdw7zevdou

Graph Optimal Transport for Cross-Domain Alignment [article]

Liqun Chen, Zhe Gan, Yu Cheng, Linjie Li, Lawrence Carin, Jingjing Liu
2020 arXiv   pre-print
In GOT, cross-domain alignment is formulated as a graph matching problem, by representing entities into a dynamically-constructed graph.  ...  Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing.  ...  The research at Duke University was supported in part by DARPA, DOE, NIH, NSF and ONR.  ... 
arXiv:2006.14744v3 fatcat:scfmjoxrsbcydcey4r5pfvejdu
« Previous Showing results 1 — 15 out of 93,714 results