Filters








3,639 Hits in 3.7 sec

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects.  ...  Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  [21] proposed structured generative adversarial networks (SGANs) for semi-supervised image classification.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks [article]

Wen-Cheng Chen, Chien-Wen Chen, Min-Chun Hu
2018 arXiv   pre-print
Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous  ...  In addition, the proposed model can achieve semi-supervised learning, which makes our model more flexible for practical applications.  ...  Kim, Jungkwon Lee, and Jiwon Kim, "Learning to discover cross-domain relations with generative adversarial networks," arXiv preprint arXiv:1703.05192, 2017.  ... 
arXiv:1804.00410v1 fatcat:ehtwl7wfkfdclo2k2svtfe4zqe

SCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network [article]

Jian Zhang, Yuxin Peng, Mingkuan Yuan
2018 arXiv   pre-print
To address these problems, in this paper we propose a novel Semi-supervised Cross-Modal Hashing approach by Generative Adversarial Network (SCH-GAN).  ...  The main contributions can be summarized as follows: (1) We propose a novel generative adversarial network for cross-modal hashing.  ...  Index Terms-Cross-modal hashing, generative adversarial network, semi-supervised. I.  ... 
arXiv:1802.02488v1 fatcat:3zxx64d7eza6xk6gt4rkmyb4vq

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Anirudh Choudhary, Li Tong, Yuanda Zhu, May D. Wang
2020 IMIA Yearbook of Medical Informatics  
, image modality, and learning scenarios.  ...  Conclusion: DA has emerged as a promising solution to deal with the lack of annotated training data.  ...  ., [58] used semi-supervised DA with paired CT images to constrain CycleGAN to generate more realistic images.  ... 
doi:10.1055/s-0040-1702009 pmid:32823306 fatcat:gtlhoh6m3fh4hcumfzdlpdohr4

Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning [article]

Arnab Kumar Mondal, Jose Dolz, Christian Desrosiers
2018 arXiv   pre-print
Leveraging the recent success of adversarial learning for semi-supervised segmentation, we propose a novel method based on Generative Adversarial Networks (GANs) to train a segmentation model with both  ...  Our work extends current adversarial learning approaches, which focus on 2D single-modality images, to the more challenging context of 3D volumes of multiple modalities.  ...  Leveraging the recent success of adversarial learning for semi-supervised segmentation, we propose a novel method based on Generative Adversarial Networks (GANs) to train a segmentation model with both  ... 
arXiv:1810.12241v1 fatcat:qqlum7slw5hmvneyh7y5rqazwu

X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data [article]

Danfeng Hong, Naoto Yokoya, Gui-Song Xia, Jocelyn Chanussot, Xiao Xiang Zhu
2020 arXiv   pre-print
This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing.  ...  Significantly, X-ModalNet generalizes well, owing to propagating labels on an updatable graph constructed by high-level features on the top of the network, yielding semi-supervised cross-modality learning  ...  Method Overview and Contributions Towards the aforementioned goals, a novel cross-modal DL framework is proposed in a semi-supervised fashion, called X-ModalNet, for RS image classification.  ... 
arXiv:2006.13806v1 fatcat:3b47auxsb5fzvc74uim5kkhwhm

A Decade Survey of Content Based Image Retrieval using Deep Learning [article]

Shiv Ram Dubey
2020 arXiv   pre-print
The taxonomy used in this survey covers different supervision, different networks, different descriptor type and different retrieval type.  ...  Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval.  ...  The adversarial neural network is also employed for cross-modal retrieval such as adversarial cross-modal retrieval (ACMR) [169] , self-supervised adversarial hashing (SSAH) [126] , attention-aware deep  ... 
arXiv:2012.00641v1 fatcat:2zcho2szpzcc3cs6uou3jpcley

Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training [article]

Harrison Nguyen, Simon Luo, Fabio Ramos
2019 arXiv   pre-print
In this work, we develop a method to address these issues with semi-supervised learning in translating between two neuroimaging modalities.  ...  Our proposed model, Semi-Supervised Adversarial CycleGAN (SSA-CGAN), uses an adversarial loss to learn from unpaired data points, cycle loss to enforce consistent reconstructions of the mappings and another  ...  Our method uses multiple adversarial signals for semi-supervised bi-directional image translation.  ... 
arXiv:1912.04391v1 fatcat:x6iyb7stjreezjayzmli2klb3e

Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions [article]

Anil Rahate, Rahee Walambe, Sheela Ramanna, Ketan Kotecha
2021 arXiv   pre-print
Multimodal deep learning systems which employ multiple modalities like text, image, audio, video, etc., are showing better performance in comparison with individual modalities (i.e., unimodal) systems.  ...  The various techniques employed to include the latest ones are reviewed along with some of the applications and datasets.  ...  GAN generates the samples for the target domain for audio-visual cross-modal mapping in [110] dacssGAN (Domain Adaptation Conditional Semi-Supervised Generative Adversarial Network).  ... 
arXiv:2107.13782v2 fatcat:s4spofwxjndb7leqbcqnwbifq4

A SEMI-SUPERVISED APPROACH TO SAR-OPTICAL IMAGE MATCHING

L. H. Hughes, M. Schmitt
2019 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
In doing so we make an initial contribution towards the use of semi-supervised learning for matching SAR and optical imagery.  ...  We further gain insight into the non-complementary nature of commonly used supervised and unsupervised loss functions, as well as dataset size requirements for semi-supervised matching.</p>  ...  Taking a different approach to the problem, (Merkle et al., 2018) proposed the use of a generative adversarial network (GAN) to generate SAR-like templates from optical image patches.  ... 
doi:10.5194/isprs-annals-iv-2-w7-71-2019 fatcat:f5mqcmwp2nbfxmwdkuonif5xwy

Semi-supervised Learning Approach to Generate Neuroimaging Modalities with Adversarial Training [chapter]

Harrison Nguyen, Simon Luo, Fabio Ramos
2020 Lecture Notes in Computer Science  
Our proposed model, Semi-Supervised Adversarial CycleGAN (SSA-CGAN), uses an adversarial loss to learn from unpaired data points, cycle loss to enforce consistent reconstructions of the mappings and another  ...  In this work, we develop a method to address these issues with semisupervised learning in translating between two neuroimaging modalities.  ...  Semi-Supervised Adversarial CycleGAN We extend the CycleGAN through the Semi-Supervised Adversarial CycleGAN (SSA-CGAN) to take advantage of paired training data.  ... 
doi:10.1007/978-3-030-47436-2_31 fatcat:wa3ang7pujhb3f23gtfkoze7xq

Semi-Supervised Haptic Material Recognition for Robots using Generative Adversarial Networks [article]

Zackory Erickson, Sonia Chernova, Charles C. Kemp
2017 arXiv   pre-print
We present a semi-supervised learning approach for material recognition that uses generative adversarial networks (GANs) with haptic features such as force, temperature, and vibration.  ...  We explore how well this approach can recognize the material of new objects and we discuss challenges facing generalization.  ...  Semi-Supervised Learning with GANs A generative adversarial network (GAN) consists of a minimax adversarial game between a generator, G, and a discriminator, D [16] .  ... 
arXiv:1707.02796v2 fatcat:m7nnnfwm35autj5m6bvdfjmna4

Random Style Transfer based Domain Generalization Networks Integrating Shape and Spatial Information [article]

Lei Li, Veronika A. Zimmer, Wangbin Ding, Fuping Wu, Liqin Huang, Julia A. Schnabel, Xiahai Zhuang
2020 arXiv   pre-print
In this work, we present a random style transfer network to tackle the domain generalization problem for multi-vendor and center cardiac image segmentation.  ...  The model can be trained in a semi-supervised manner by simultaneously optimizing a supervised segmentation and an unsupervised style translation objective.  ...  ., fully supervised U-Net [9] and multi-task attention-based semi-supervised learning (MASSL) network [3] .  ... 
arXiv:2008.12205v2 fatcat:fum5rewuuvcz7fwlyjhnnsfnki

MTANS: Multi-Scale Mean Teacher Combined Adversarial Network with Shape-Aware Embedding for Semi-Supervised Brain Lesion Segmentation

Gaoxiang Chen, Jintao Ru, Yilin Zhou, Islem Rekik, Zhifang Pan, Xiaoming Liu, Yezhi Lin, Beichen Lu, Jialin Shi
2021 NeuroImage  
In this paper, we propose a novel semi-supervised segmentation framework that combines improved mean teacher and adversarial network.  ...  Experiments demonstrate that our method can effectively leverage unlabeled data while outperforming the supervised baseline and other state-of-the-art semi-supervised methods trained with the same labeled  ...  network, that was the state-of-the-art semi-supervised segmentation method for natural images.  ... 
doi:10.1016/j.neuroimage.2021.118568 pmid:34508895 fatcat:a3435uosm5ddjprfizn5obb6um

Cycle-Consistent Deep Generative Hashing for Cross-Modal Retrieval

Lin Wu, Yang Wang, Ling Shao
2019 IEEE Transactions on Image Processing  
In this paper, we propose a novel deep generative approach to cross-modal retrieval to learn hash functions in the absence of paired training samples through the cycle consistency loss.  ...  To induce the hash codes with semantics to the input-output pair, cycle consistency loss is further proposed upon the adversarial training to strengthen the correlations between inputs and corresponding  ...  Query examples Cross-modal data set Cross-modal retrieval results Recent works have shown that generative adversarial networks combined with cycle-consistency constraints are surprisingly effective at  ... 
doi:10.1109/tip.2018.2878970 fatcat:oy33fwr4mje5fd2njqzmioeq2a
« Previous Showing results 1 — 15 out of 3,639 results