1,992 Hits in 4.0 sec

Semi-Supervised Learning for Optical Flow with Generative Adversarial Networks

Wei-Sheng Lai, Jia-Bin Huang, Ming-Hsuan Yang
2017 Neural Information Processing Systems  
In this paper, we propose to exploit unlabeled videos for semi-supervised learning of optical flow with a Generative Adversarial Network.  ...  Convolutional neural networks (CNNs) have recently been applied to the optical flow estimation problem.  ...  Semi-Supervised Optical Flow Estimation In this section, we describe the semi-supervised learning approach for optical flow estimation, the design methodology of the proposed generative adversarial network  ... 
dblp:conf/nips/LaiH017 fatcat:24mjzmgfvbfj5liplf7ikzyktu

SDOF-GAN: Symmetric Dense Optical Flow Estimation With Generative Adversarial Networks

Tongtong Che, Yuanjie Zheng, Yunshuai Yang, Sujuan Hou, Weikuan Jia, Jie Yang, Chen Gong
2021 IEEE Transactions on Image Processing  
We bridge this gap by introducing a novel model named SDOF-GAN: symmetric dense optical flow with generative adversarial networks (GANs).  ...  In addition, SDOF-GAN leverages a GAN model for which the generator estimates symmetric optical flow fields while the discriminator differentiates the "real" ground-truth flow field from a "fake" estimation  ...  Therefore, SDOF-GAN aims to minimize the L sup for labeled images with the ground-truth flow. 3) Adversarial Loss: To train the generator G and discriminator D with semi-supervised learning on both labeled  ... 
doi:10.1109/tip.2021.3084073 fatcat:3vsqjzcqyff6zjzkqfkbkgjqt4

Spoof Face Detection Via Semi-Supervised Adversarial Training [article]

Chengwei Chen, Wang Yuan, Xuequan Lu, Lizhuang Ma
2020 arXiv   pre-print
In this paper, we propose a semi-supervised adversarial learning framework for spoof face detection, which largely relaxes the supervision condition.  ...  ., temporal information), we intuitively take the optical flow maps converted from consecutive video frames as input.  ...  Motivated by the above limitations and analysis, we propose a novel adversarial network for anti-spoofing under the semi-supervised setting.  ... 
arXiv:2005.10999v1 fatcat:akn3bbfdgrczzdb476ym2ohiyy


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.  ...  In this paper we frame the matching problem within semi-supervised learning, and use this as a proxy for investigating the effects of data scarcity on matching.  ...  of semi-supervised learning for SAR-optical matching.  ... 
doi:10.5194/isprs-annals-iv-2-w7-71-2019 fatcat:f5mqcmwp2nbfxmwdkuonif5xwy

Dual Discriminator Generative Adversarial Network for Video Anomaly Detection

Fei Dong, Yu Zhang, Xiushan Nie
2020 IEEE Access  
In this paper, we propose a semi-supervised approach with a dual discriminator-based generative adversarial network structure.  ...  Fake optical flows are estimated from generated frames and adjacent frames, and real optical flows are estimated from the real frames sampled from original videos.  ...  the stateof-the-art performance for semi-supervised video anomaly detection.  ... 
doi:10.1109/access.2020.2993373 fatcat:y7qrrnapcnbp3agngpwkr5csp4

Retinal Image Synthesis and Semi-supervised Learning for Glaucoma Assessment

Andres Diaz-Pinto, Adrian Colomer, Valery Naranjo, Sandra Morales, Yanwu Xu, Alejandro F Frangi
2019 IEEE Transactions on Medical Imaging  
Recent works show that generative adversarial networks (GANs) can be successfully applied to image synthesis and semi-supervised learning, where, given a small labeled database and a large unlabeled database  ...  In this paper, we trained a retinal image synthesizer and a semi-supervised learning method for automatic glaucoma assessment using an adversarial model on a small glaucoma-labeled database and a large  ...  ACKNOWLEDGMENT We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.  ... 
doi:10.1109/tmi.2019.2903434 pmid:30843823 fatcat:2rq7d3uag5gzdjc6uecacdvqya

Adversarial Framework for Unsupervised Learning of Motion Dynamics in Videos [article]

C. Spampinato, S. Palazzo, P. D'Oro, D. Giordano, M. Shah
2019 arXiv   pre-print
Self-supervision is enforced by using motion masks produced by the generator, as a co-product of its generation process, to supervise the discriminator network in performing dense prediction.  ...  In this paper, we propose an adversarial GAN-based framework that learns video representations and dynamics through a self-supervision mechanism in order to perform dense and global prediction in videos  ...  the optical flow dense prediction stream and using masks synthesized by the generator for supervision.  ... 
arXiv:1803.09092v2 fatcat:tconl7knq5af3nqlbxthvx7br4

A Conditional Adversarial Network for Scene Flow Estimation [article]

Ravi Kumar Thakur, Snehasis Mukherjee
2019 arXiv   pre-print
The proposed network is the first attempt to estimate scene flow using generative adversarial networks, and is able to estimate both the optical flow and disparity from the input stereo images simultaneously  ...  We propose a conditional adversarial network SceneFlowGAN for scene flow estimation. The proposed SceneFlowGAN uses loss function at two ends: both generator and descriptor ends.  ...  There are a few learning based methods for scene flow estimation. This can be useful in semi-supervised learning scenario as well, since acquiring data will remain a challenge.  ... 
arXiv:1904.11163v1 fatcat:ztnbw3quxzcohoiqvx7dctml5i

Monocular Depth Estimation Based On Deep Learning: An Overview [article]

Chaoqiang Zhao, Qiyu Sun, Chongzhen Zhang, Yang Tang, Feng Qian
2020 arXiv   pre-print
Furthermore, we review some representative existing methods according to different training manners: supervised, unsupervised and semi-supervised.  ...  With the rapid development of deep neural networks, monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy.  ...  Similarly, considering that optical flow is successfully solved by CNN through supervised learning, Mayer et al. [33] extend the optical flow networks to disparity and scene flow estimation.  ... 
arXiv:2003.06620v1 fatcat:l5ei3ognova6xkyppflef5nqsq

A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis [chapter]

Yonghui Fan, Gang Wang, Natasha Lepore, Yalin Wang
2018 Lecture Notes in Computer Science  
Quality Metric 596 Fully Automated Blind Color Deconvolution of Histopathological Images 599 A Pixel-wise Distance Regression Approach for Joint Retinal Optical Disc and Fovea Detection 606 Semi-supervised  ...  for Fast Probabilistic Diffeomorphic Registration 286 Conditional Entropy as a Supervised Primitive Segmentation Loss Function 290 Adversarial Similarity Network for Evaluating Image Alignment in Deep  ... 
doi:10.1007/978-3-030-00931-1_48 pmid:30338317 pmcid:PMC6191198 fatcat:dqhvpm5xzrdqhglrfftig3qejq

Spatiotemporal CNN for Video Object Segmentation [article]

Kai Xu, Longyin Wen, Guorong Li, Liefeng Bo, Qingming Huang
2019 arXiv   pre-print
The spatial segmentation branch focuses on segmenting objects accurately based on the learned appearance and motion cues.  ...  In this paper, we present a unified, end-to-end trainable spatiotemporal CNN model for VOS, which consists of two branches, i.e., the temporal coherence branch and the spatial segmentation branch.  ...  Notably, in contrast to [25] , we do not generate the optical flow since our STCNN do not require the optical flow for video segmentation.  ... 
arXiv:1904.02363v1 fatcat:mmzxevx4hrcdzfnllksl6pyrjy

Adversarial Learning for Semi-Supervised Semantic Segmentation [article]

Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou, Yen-Yu Lin, Ming-Hsuan Yang
2018 arXiv   pre-print
We propose a method for semi-supervised semantic segmentation using an adversarial network.  ...  In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory  ...  [40] propose to generate adversarial examples using GAN for semi-supervised semantic segmentation.  ... 
arXiv:1802.07934v2 fatcat:vzcurbdrgzdfflikr6sdjup6um

DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks [article]

Unaiza Ahsan, Chen Sun, Irfan Essa
2018 arXiv   pre-print
We determine good network architectural and hyperparameter settings for us- ing the discriminator from DCGAN as a trained model to learn useful representations for action recognition.  ...  Our model involves train- ing a deep convolutional generative adversarial network (DCGAN) using a large video activity dataset without la- bel information.  ...  Generative Adversarial Networks [4] have been used for semi-supervised feature learning particularly after the introduction of Deep Convolutional GANs (or DCGANs) [38] .  ... 
arXiv:1801.07230v1 fatcat:jadecr4slffrtezim3lrr2klva

Generation and Simulation of Yeast Microscopy Imagery with Deep Learning [article]

Christoph Reich
2021 arXiv   pre-print
To approach this problem, a novel generative adversarial network, for conditionalized and unconditionalized image generation, is proposed.  ...  The obtained results showed that the modeling of TLFM experiments, with deep learning, is a proper approach, but requires future research to effectively model real-world experiments.  ...  .5 Semi Supervised Learning . 6 Semantic Segmentation .7 Optical Flow .1 Improved Generative Adversarial Network Methods .1 Improved Generative Adversarial Network Methods .1  ... 
arXiv:2103.11834v4 fatcat:x6jljdhd4vcx7a3wjxj6igs57q

Deep learning approaches for real-time image super-resolution

Pourya Shamsolmoali, M. Emre Celebi, Ruili Wang
2020 Neural computing & applications (Print)  
The paper entitled "Perceptual image quality using dual generative adversarial network" develops a variety of generative adversarial networks for image SR that contains two generators and two discriminators  ...  Recently, due to remarkable advances in deep learning, deep neural networks for SR have shown promising performance in several applications.  ...  The paper ''A novel super-resolution CT image reconstruction via semi-supervised generative adversarial network'' proposes a novel semi-supervised generative adversarial network to accurately recover HR  ... 
doi:10.1007/s00521-020-05176-z fatcat:gvmbzve6kvfmzfwumblipqzaji
« Previous Showing results 1 — 15 out of 1,992 results